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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions and symbols used in scientific equations

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

    math notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.54
     صوتيه
    -0.45
     ErrIntOverflow
    -0.43
    REWRITE
    -0.42
    amplific
    -0.40
     foon
    -0.37
     cherchés
    -0.37
     Signalez
    -0.36
    arab
    -0.36
    تقاوى
    -0.36
    POSITIVE LOGITS
    StructEnd
    0.59
    Personendaten
    0.44
    AndFlush
    0.42
    issner
    0.42
    tgär
    0.41
    PreferredItem
    0.41
    oolean
    0.40
    tagHelperRunner
    0.39
     and
    0.39
     systematically
    0.39
    Act Density 0.240%

    No Known Activations