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

    Neuronpedia

    INDEX
    Explanations

    biased

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scenic
    -0.09
    ำเภ
    -0.08
     rése
    -0.08
     yoga
    -0.08
     Bairro
    -0.08
     Parque
    -0.08
    Adornment
    -0.08
     intersect
    -0.08
    ê
    -0.08
    Volunteer
    -0.08
    POSITIVE LOGITS
     unusual
    0.10
     biased
    0.10
     calibration
    0.09
     необы
    0.09
     unusually
    0.09
     horrible
    0.09
     tweaks
    0.08
    biased
    0.08
     malfunction
    0.08
     raro
    0.08
    Act Density 0.009%

    No Known Activations