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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izontal
    -0.07
     necessarily
    -0.06
    CRET
    -0.06
    済
    -0.06
    restricted
    -0.06
    سان
    -0.06
    regulated
    -0.06
    -component
    -0.06
    .GeneratedValue
    -0.06
    무
    -0.06
    POSITIVE LOGITS
     모르
    0.07
     práva
    0.07
    _likelihood
    0.07
    referer
    0.07
     +:+
    0.07
    特色
    0.06
     Taliban
    0.06
    .pickle
    0.06
     Wasser
    0.06
    irse
    0.06
    Act Density 0.037%

    No Known Activations