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

    Neuronpedia

    INDEX
    Explanations

    Human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @",
    -0.08
    روی
    -0.08
     messageId
    -0.07
    .sqrt
    -0.06
    .set
    -0.06
    Encrypt
    -0.06
    .Release
    -0.06
     paired
    -0.06
    дает
    -0.06
    _events
    -0.06
    POSITIVE LOGITS
    dropdown
    0.08
     eCommerce
    0.07
    тр
    0.07
    -cookie
    0.07
     действия
    0.07
    mui
    0.07
     요
    0.06
    Never
    0.06
     irresistible
    0.06
     Kn
    0.06
    Act Density 0.002%

    No Known Activations