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

    Neuronpedia

    INDEX
    Explanations

    substrings of proper names that might come from a non-English language

    oai_token-act-pair · gemini-2.0-flash

    Wikipedia article names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.65
    featureID
    -0.65
    thâu
    -0.64
     numerus
    -0.57
    ImageContext
    -0.57
    ViewFeatures
    -0.56
    GEBURTSDATUM
    -0.56
    sizeCache
    -0.55
     MacLeod
    -0.54
    SourceChecksum
    -0.53
    POSITIVE LOGITS
    viation
    0.52
     ruling
    0.44
     warmest
    0.43
    ArgsConstructor
    0.43
     nhật
    0.42
     primaire
    0.42
    AxisAlignment
    0.42
    alva
    0.41
    hint
    0.41
     rule
    0.41
    Act Density 0.425%

    No Known Activations