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

    Neuronpedia

    INDEX
    Explanations

    newsletter signups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     submissive
    -0.08
    362
    -0.07
    ドル
    -0.07
     toho
    -0.07
    _song
    -0.07
    .***.***
    -0.07
     začí
    -0.06
    �
    -0.06
     мати
    -0.06
     bilgileri
    -0.06
    POSITIVE LOGITS
    inox
    0.08
     advanced
    0.07
    ρωση
    0.07
     perpet
    0.06
    Curve
    0.06
    stay
    0.06
     quarter
    0.06
     uncover
    0.06
     Morrow
    0.06
     پرو
    0.06
    Act Density 0.007%

    No Known Activations