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

    Neuronpedia

    INDEX
    Explanations

    words related to inherent qualities or occurrences

    oai_token-act-pair · gemini-2.0-flash

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.88
     تضيفلها
    -0.84
     متعلقه
    -0.77
     Efq
    -0.74
    ValueStyle
    -0.74
    BeginContext
    -0.68
     يتيمه
    -0.68
    MLLoader
    -0.68
    contentLoaded
    -0.68
     שוליים
    -0.68
    POSITIVE LOGITS
     natural
    1.34
    natural
    1.20
     naturales
    1.18
     Natural
    1.16
     NATURAL
    1.13
    NATURAL
    1.11
    Natural
    1.10
     naturally
    1.10
     naturais
    1.09
     naturale
    1.05
    Act Density 1.534%

    No Known Activations