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

    Neuronpedia

    INDEX
    Explanations

    detailed

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that emphasize a thorough experimental or analytical effort (e.g. “detailed study,” “thorough investigation,” “analysis,” “performed”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     petroleum
    -0.07
     Ubisoft
    -0.07
     трьох
    -0.06
     gmail
    -0.06
     analyst
    -0.06
    (city
    -0.06
     south
    -0.06
     gson
    -0.06
    трон
    -0.06
    afc
    -0.06
    POSITIVE LOGITS
    binding
    0.07
     Ends
    0.07
    having
    0.07
     animated
    0.07
    .Hidden
    0.06
    ksam
    0.06
    +p
    0.06
    jylland
    0.06
    {(
    0.06
    UniqueId
    0.06
    Act Density 0.014%

    No Known Activations