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

    Neuronpedia

    INDEX
    Explanations

    op

    np_max-act · gemini-2.0-flash

    text related to scientific research and studies on skin healing and growth factors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron selectively activates on occurrences of the preposition “from.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    isiert
    -0.07
     yielding
    -0.07
    (strcmp
    -0.07
     Hedge
    -0.07
    ejte
    -0.06
     Witness
    -0.06
     yog
    -0.06
    (stats
    -0.06
     disdain
    -0.06
     стану
    -0.06
    POSITIVE LOGITS
    utter
    0.07
     wired
    0.06
     Some
    0.06
    ุค
    0.06
    currentTime
    0.06
    кий
    0.06
     ###↵
    0.06
     signing
    0.06
     birim
    0.06
     generator
    0.06
    Act Density 0.000%

    No Known Activations