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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting characters typically used in code and documentation

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

    nails driven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.86
     للمعارف
    -0.81
    IsContent
    -0.80
    IVEREF
    -0.79
    AndEndTag
    -0.79
    setVerticalGroup
    -0.78
    principalTable
    -0.77
     محفوظة
    -0.75
     ProtoMessage
    -0.75
    aarrggbb
    -0.73
    POSITIVE LOGITS
     catch
    0.29
     kö
    0.29
     яй
    0.28
    kø
    0.28
    TypeID
    0.28
     kew
    0.26
    .*;
    0.26
     Social
    0.26
    对他
    0.26
     egg
    0.26
    Act Density 0.001%

    No Known Activations