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

    Neuronpedia

    INDEX
    Explanations

    Status

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    输出
    -0.08
     puesto
    -0.07
    MH
    -0.07
     deck
    -0.07
    .links
    -0.07
     piston
    -0.07
    outs
    -0.06
     floor
    -0.06
    _PI
    -0.06
    -out
    -0.06
    POSITIVE LOGITS
    [min
    0.07
    .errors
    0.06
     Canadian
    0.06
     تبدیل
    0.06
    анта
    0.06
     世
    0.06
    )↵↵↵↵↵↵
    0.06
    ={{↵
    0.06
     seamlessly
    0.06
    采
    0.06
    Act Density 0.016%

    No Known Activations