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

    Neuronpedia

    INDEX
    Explanations

    Less than sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     architectures
    -0.08
     gasoline
    -0.08
    '])↵↵
    -0.07
     вона
    -0.06
     Jew
    -0.06
     sport
    -0.06
    图片
    -0.06
     Pictures
    -0.06
     Dubai
    -0.06
    _lazy
    -0.06
    POSITIVE LOGITS
     Lauderdale
    0.07
     Seah
    0.06
     возникнов
    0.06
     Mehmet
    0.06
    .Compare
    0.06
     еще
    0.06
    isRequired
    0.06
    DivElement
    0.06
    .Enable
    0.06
    ود
    0.06
    Act Density 0.003%

    No Known Activations