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

    Neuronpedia

    INDEX
    Explanations

    questions about attending, extra, device, email

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.85
    ‌ی
    0.84
    cfg
    0.81
     behavioral
    0.77
     connectors
    0.73
    tt
    0.71
    ای
    0.70
    czny
    0.70
    p
    0.69
    kp
    0.68
    POSITIVE LOGITS
     sür
    0.81
     sambil
    0.76
     após
    0.75
     thử
    0.75
     ngành
    0.75
     спра
    0.73
     вместе
    0.70
     eosin
    0.70
     nữ
    0.70
     nemá
    0.70
    Act Density 0.001%

    No Known Activations