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

    Neuronpedia

    INDEX
    Explanations

    programming import statements

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

    Code, specifically imports or code snippets

    np_acts-logits-general · gemini-2.0-flash

    code blocks and programming imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.75
    principalColumn
    -0.74
     ModelExpression
    -0.66
     utafitiHapana
    -0.65
    featureID
    -0.65
     trasparente
    -0.63
    addCriterion
    -0.62
    EndGlobalSection
    -0.62
    shadowOffset
    -0.62
    SharedDtor
    -0.60
    POSITIVE LOGITS
     {
    1.30
     *
    0.90
     {
    0.82
    {
    0.78
     {}
    0.65
     type
    0.63
     './
    0.58
     «
    0.58
     {//
    0.56
     {\
    0.55
    Act Density 0.021%

    No Known Activations