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

    Neuronpedia

    INDEX
    Explanations

    notes information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     womens
    -0.07
    <typeof
    -0.06
     شیمی
    -0.06
     खड
    -0.06
     lonely
    -0.06
    _helpers
    -0.06
     zaměstn
    -0.06
    _PED
    -0.06
     kvinne
    -0.06
     peč
    -0.06
    POSITIVE LOGITS
    (remove
    0.07
    nette
    0.07
     observed
    0.07
    нок
    0.06
     actions
    0.06
    Ever
    0.06
    Tier
    0.06
    告
    0.06
     Guinea
    0.06
    ้น
    0.06
    Act Density 0.004%

    No Known Activations