Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    gradient

    np_max-act · gemini-2.0-flash

    The neuron is triggered by scientific mentions of physical or chemical gradients (e.g. “vapor pressure gradient,” “concentration gradient,” “temperature gradient”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms and concepts related to membrane distillation technology.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    anth
    -0.07
     userType
    -0.07
    cluster
    -0.07
     mailbox
    -0.07
    Kir
    -0.06
    million
    -0.06
    _character
    -0.06
     words
    -0.06
     Dust
    -0.06
     плани
    -0.06
    POSITIVE LOGITS
     Difference
    0.07
     ступ
    0.06
    анк
    0.06
     применения
    0.06
     шляхом
    0.06
     eagerly
    0.06
     donde
    0.06
    (final
    0.06
     prohibition
    0.06
     RuntimeError
    0.06
    Act Density 0.008%

    No Known Activations