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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ber
    -0.07
    нять
    -0.06
     مور
    -0.06
    Cold
    -0.06
    Deep
    -0.06
    _lim
    -0.06
     péče
    -0.06
    bindValue
    -0.06
    bounds
    -0.06
     boldly
    -0.06
    POSITIVE LOGITS
     Minority
    0.07
    .Timeout
    0.07
    陰
    0.06
    haul
    0.06
    drivers
    0.06
    VF
    0.06
     pollut
    0.06
     Static
    0.06
     ignored
    0.06
    gı
    0.06
    Act Density 0.002%

    No Known Activations