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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and identifiers in code or data formats

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

    hex or alphanumeric identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XtraReports
    -0.79
     للاسماء
    -0.78
    fjspx
    -0.66
     nahilalakip
    -0.65
    SequentialGroup
    -0.65
     estekak
    -0.64
     ModelExpression
    -0.64
     فريبيس
    -0.63
    tonode
    -0.60
    WebVitals
    -0.60
    POSITIVE LOGITS
     graça
    0.42
     nasional
    0.40
     Geschle
    0.39
     bancaria
    0.36
     tuoi
    0.35
     berço
    0.35
     pescoço
    0.35
     Atlántico
    0.34
     caminhão
    0.34
     Vernunft
    0.33
    Act Density 0.052%

    No Known Activations