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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exist
    -0.07
     minha
    -0.07
     differ
    -0.07
    ност
    -0.07
    习近平总
    -0.07
     statistically
    -0.07
    ﲒ
    -0.07
    _FOLDER
    -0.07
    <View
    -0.06
    .SIG
    -0.06
    POSITIVE LOGITS
    궂
    0.07
     Gundam
    0.07
     Highlands
    0.07
     autos
    0.07
    -faced
    0.07
    -New
    0.07
    Investigators
    0.06
     PLAYER
    0.06
    .Warn
    0.06
    .Designer
    0.06
    Act Density 0.076%

    No Known Activations