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

    Neuronpedia

    INDEX
    Explanations

    strings of characters mostly composed of whitespace

    oai_token-act-pair · gemini-2.0-flash

    Reference webpage excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olerance
    -0.58
     Offisielt
    -0.54
     ghiaccio
    -0.53
     الحره
    -0.52
     ويكي
    -0.52
     Toler
    -0.50
    onzo
    -0.50
     heapq
    -0.48
    Union
    -0.48
    وصلات
    -0.47
    POSITIVE LOGITS
    исленность
    0.65
    IndentedString
    0.63
    InjectAttribute
    0.62
    Personendaten
    0.59
     invi
    0.59
     transfieras
    0.57
    tagext
    0.56
    ntesis
    0.56
     OMIT
    0.55
    ртуаль
    0.55
    Act Density 1.037%

    No Known Activations