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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owers
    -0.06
     Pink
    -0.06
    @admin
    -0.06
     hunting
    -0.06
    [element
    -0.06
    aras
    -0.06
     facts
    -0.06
    -blue
    -0.06
    pink
    -0.06
    Categories
    -0.06
    POSITIVE LOGITS
    FB
    0.07
    änn
    0.06
    .ng
    0.06
    OP
    0.06
    خانه
    0.06
    seud
    0.06
    syscall
    0.06
     Inspection
    0.06
    .ball
    0.06
    ॉट
    0.06
    Act Density 0.019%

    No Known Activations