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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of numbers and associated symbols

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

    more detail OR image files OR numbers/codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.67
     Chwiliwch
    -0.65
    PyExc
    -0.63
     ModelExpression
    -0.60
    WithIOException
    -0.58
    ActionCreators
    -0.56
    GOTREF
    -0.56
    RTEE
    -0.54
    IsMutable
    -0.52
    addCriterion
    -0.52
    POSITIVE LOGITS
    tikan
    0.39
     pictured
    0.36
     Dag
    0.36
     RESPECT
    0.34
    NECTION
    0.34
     Barros
    0.34
    kanan
    0.33
     Ganze
    0.33
    Dag
    0.33
    ậ
    0.33
    Act Density 0.010%

    No Known Activations