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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PID
    -0.07
    _q
    -0.07
     pon
    -0.07
     ओ
    -0.07
     sample
    -0.06
    Joy
    -0.06
    SU
    -0.06
    (member
    -0.06
     Bor
    -0.06
     vulgar
    -0.06
    POSITIVE LOGITS
    appendChild
    0.06
    came
    0.06
    CENT
    0.06
     Schwar
    0.06
     жов
    0.06
     ull
    0.06
    0.06
    gage
    0.05
    urls
    0.05
    شب
    0.05
    Act Density 0.000%

    No Known Activations