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

    Neuronpedia

    INDEX
    Explanations

    clock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -heading
    -0.08
    (height
    -0.08
    android
    -0.08
    sidebar
    -0.07
    处方
    -0.07
    (argument
    -0.07
    numeric
    -0.07
     Orig
    -0.07
    .]
    -0.07
    ()]
    -0.07
    POSITIVE LOGITS
    却被
    0.07
    就被
    0.07
     мало
    0.07
    Ằ
    0.07
     требуется
    0.07
    .ProgressBar
    0.07
     película
    0.07
    Quite
    0.07
    廠
    0.07
    ERY
    0.07
    Act Density 0.027%

    No Known Activations