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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and mathematical notation

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

    conditional math formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Opening
    -0.43
     opening
    -0.40
     appealing
    -0.39
    Opening
    -0.38
     Brenn
    -0.35
     OPENING
    -0.34
     Behind
    -0.34
    chenta
    -0.33
     pojed
    -0.33
    initWith
    -0.33
    POSITIVE LOGITS
    awtextra
    0.59
     surla
    0.59
    MessageOf
    0.56
     Walkover
    0.54
    TypedDataSet
    0.49
    ########.
    0.49
     HasFactory
    0.49
    ImageContext
    0.48
    AddTagHelper
    0.48
    LEncoder
    0.46
    Act Density 0.126%

    No Known Activations