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

    Neuronpedia

    INDEX
    Explanations

    10-K, 10-Q, peristalsis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lichaam
    0.77
    ToWrite
    0.73
    लॉक
    0.71
    <h4>
    0.70
    زن
    0.69
    lock
    0.68
     inden
    0.68
    TimeTo
    0.67
    ውነ
    0.64
    body
    0.64
    POSITIVE LOGITS
    FeO
    0.76
     nomen
    0.64
    ম্ব
    0.63
     monks
    0.62
     preval
    0.61
     rob
    0.60
     romana
    0.60
     кабинет
    0.59
     soll
    0.59
    RM
    0.59
    Act Density 0.002%

    No Known Activations