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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric data and its representation in various formats

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

    Mathematical or statistical notation/symbols

    np_acts-logits-general · gemini-2.0-flash

    probabilitiesp-valuesstatisticscoordinatesmeasurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.41
     tatuagem
    -0.40
     fumée
    -0.36
     boxeo
    -0.35
     bonté
    -0.34
    DoubleQuotes
    -0.34
     mierda
    -0.33
     camiset
    -0.33
     agujas
    -0.33
     crochê
    -0.33
    POSITIVE LOGITS
     فريبيس
    0.68
    InjectAttribute
    0.63
    fjspx
    0.59
    SharedDtor
    0.57
     Italijanski
    0.55
    Географиясе
    0.53
    UnusedPrivate
    0.52
    IBOutlet
    0.52
    Espèce
    0.52
    FieldOffsetTable
    0.51
    Act Density 1.715%

    No Known Activations