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

    Neuronpedia

    INDEX
    Explanations

    structures and symbols used in mathematical expressions or equations

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

    math notations and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.73
    parsedMessage
    -0.63
    UrlResolution
    -0.59
     ModelExpression
    -0.59
    CharacterOffset
    -0.55
    rawDesc
    -0.53
     esternos
    -0.50
    GEBURTSDATUM
    -0.50
    RenderAtEndOf
    -0.50
    TagMode
    -0.48
    POSITIVE LOGITS
    +#+
    0.44
    icznie
    0.41
     éste
    0.39
     estekak
    0.37
     ésta
    0.34
     @"";
    0.34
     ";"
    0.34
    MIT
    0.33
    ControllerAdvice
    0.33
     ‪
    0.32
    Act Density 0.024%

    No Known Activations