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

    Neuronpedia

    INDEX
    Explanations

    file path components and symbols commonly used in programming or web development

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

    Code paths or file paths

    np_acts-logits-general · gemini-2.0-flash

    file paths and module names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.45
     vœux
    -0.43
     pouvoit
    -0.39
     appui
    -0.37
     húmedo
    -0.36
     juicio
    -0.35
     plais
    -0.35
    Citiți
    -0.35
     ProtoMessage
    -0.35
     vícti
    -0.34
    POSITIVE LOGITS
    OGND
    0.75
     informée
    0.59
    __(/*!
    0.57
    jspb
    0.56
    RenderAtEndOf
    0.55
    LookAnd
    0.54
    Portale
    0.54
    
    0.54
    fjspx
    0.54
     digress
    0.53
    Act Density 0.130%

    No Known Activations