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

    Neuronpedia

    INDEX
    Explanations

    Software/gaming context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Oper
    -0.08
    不仅是
    -0.07
     wearing
    -0.07
    hide
    -0.07
    _abs
    -0.07
    滴
    -0.07
     Jog
    -0.06
    TextStyle
    -0.06
     Cricket
    -0.06
    跳出
    -0.06
    POSITIVE LOGITS
     Plato
    0.07
     Büro
    0.07
     TD
    0.07
    uição
    0.06
    館
    0.06
    谎言
    0.06
    .Errors
    0.06
     bases
    0.06
     careers
    0.06
    baum
    0.06
    Act Density 0.007%

    No Known Activations