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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    属
    -0.07
     вполне
    -0.07
    }><
    -0.06
    cohol
    -0.06
     навіть
    -0.06
    och
    -0.06
    html
    -0.06
     bras
    -0.06
    StrLn
    -0.06
    Thor
    -0.06
    POSITIVE LOGITS
    rate
    0.07
    /rs
    0.06
    _HC
    0.06
    -handle
    0.06
     identity
    0.06
     defenses
    0.06
    行为
    0.06
    .codes
    0.06
     directly
    0.06
    .microsoft
    0.06
    Act Density 0.055%

    No Known Activations