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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    include
    -0.45
     jutaan
    -0.43
    昔
    -0.42
    nice
    -0.42
    sem
    -0.41
    rite
    -0.41
     olvides
    -0.41
    une
    -0.41
    軍
    -0.41
    :+:
    -0.40
    POSITIVE LOGITS
     ContentValues
    0.72
     يتيمه
    0.71
    TagMode
    0.66
    Personendaten
    0.65
    Hochspringen
    0.63
    tagHelperRunner
    0.62
    IContainer
    0.61
    AutoField
    0.61
    cotch
    0.58
     مشين
    0.58
    Act Density 0.023%

    No Known Activations