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

    Neuronpedia

    INDEX
    Explanations

    code-related elements, particularly class definitions and imports in programming languages

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

    code imports and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.73
    WriteBarrier
    -0.67
    -------------</
    -0.65
    GraphicsUnit
    -0.65
    Personendaten
    -0.64
     Wikimedijinoj
    -0.60
     Infórmanos
    -0.60
    Hozzáférés
    -0.60
    Bakgrunnsstoff
    -0.60
     Exactos
    -0.59
    POSITIVE LOGITS
    import
    0.50
    derive
    0.36
     a
    0.35
    Came
    0.34
    class
    0.31
     an
    0.31
    Cos
    0.31
    接受
    0.30
    Imagine
    0.30
    テック
    0.30
    Act Density 0.001%

    No Known Activations