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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    люд
    -0.07
    ھ
    -0.06
    楚
    -0.06
     非
    -0.06
     благ
    -0.06
     эксплуата
    -0.06
    (Module
    -0.06
    周期
    -0.06
    timing
    -0.06
     Deus
    -0.06
    POSITIVE LOGITS
    ادر
    0.06
     μέρος
    0.06
     große
    0.06
    Scalars
    0.06
     Separator
    0.06
    onDelete
    0.06
    adro
    0.06
    andReturn
    0.06
    kish
    0.06
     selections
    0.06
    Act Density 0.149%

    No Known Activations