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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal codes and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unsubscribe
    1.10
     smoothing
    1.10
     CCD
    1.04
    ন
    1.03
     smoothed
    1.03
    okra
    1.03
     castes
    1.02
    okkal
    1.02
     telemedicine
    1.00
    odils
    0.99
    POSITIVE LOGITS
    чий
    0.95
     partidos
    0.87
     правой
    0.85
    body
    0.84
     pequenos
    0.83
    이스
    0.82
     שלי
    0.81
    IH
    0.80
     Teraz
    0.80
    ѧ
    0.79
    Act Density 0.000%

    No Known Activations