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

    Neuronpedia

    INDEX
    Explanations

    to be verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     came
    -0.08
     became
    -0.08
     grew
    -0.08
    :].
    -0.07
     徒歩
    -0.07
     estava
    -0.07
     vardı
    -0.07
     tenía
    -0.07
     consisted
    -0.07
     was
    -0.06
    POSITIVE LOGITS
    imited
    0.07
    _decl
    0.07
     Зам
    0.06
    Quarter
    0.06
    .Raw
    0.06
     regeneration
    0.06
    Constants
    0.06
    Merc
    0.06
    oggles
    0.06
     Padding
    0.06
    Act Density 0.332%

    No Known Activations