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

    Neuronpedia

    INDEX
    Explanations

    instances of statements or expressions relating to error handling

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

    programming declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EReference
    -0.41
     préfé
    -0.40
    鰭
    -0.39
     négo
    -0.37
     peores
    -0.36
    Semoga
    -0.36
     dictadura
    -0.36
     excelencia
    -0.36
    ându
    -0.35
     Rücksicht
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.79
     initComponents
    0.75
     ***!
    0.74
     ujednoznacz
    0.73
    \{\\
    0.71
     يتيمه
    0.68
    ScopeManager
    0.68
    rungsseite
    0.65
    endcsname
    0.65
    0.64
    Act Density 0.002%

    No Known Activations