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

    Neuronpedia

    INDEX
    Explanations

    structured mathematical expressions or arrays

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

    LaTeX math arrays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.78
     ModelExpression
    -0.65
     متعلقه
    -0.63
     '\\;'
    -0.63
    modelBuilder
    -0.61
    IsMutable
    -0.59
    DockStyle
    -0.58
    parsedMessage
    -0.57
     HttpNotFound
    -0.57
    uxxxx
    -0.57
    POSITIVE LOGITS
    sticks
    0.37
    stick
    0.36
    Pb
    0.36
    dula
    0.34
     ref
    0.34
     Wakefield
    0.33
    Wake
    0.33
     بیت
    0.33
    /*
    0.33
     Neuk
    0.32
    Act Density 0.411%

    No Known Activations