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

    Neuronpedia

    INDEX
    Explanations

    references to construction phases and project details

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

    sections of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.42
     Spar
    -0.34
    Spar
    -0.34
     Spre
    -0.31
     Дер
    -0.31
    doc
    -0.30
    Sprintf
    -0.28
     WRONG
    -0.28
     CORRECT
    -0.26
    
    -0.26
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    SequentialGroup
    0.71
     propOrder
    0.68
     الحره
    0.68
    DockStyle
    0.67
     erſt
    0.66
    MLLoader
    0.65
    transQ
    0.63
     مشين
    0.62
     @"/
    0.61
    Act Density 0.009%

    No Known Activations