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

    Neuronpedia

    INDEX
    Explanations

    Rutgers, Rutger, Ruthenium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "
    0.86
    на
    0.84
    ת
    0.83
    ку
    0.82
    يب
    0.79
    با
    0.73
    يش
    0.73
    ك
    0.72
    غير
    0.71
    íti
    0.71
    POSITIVE LOGITS
    el
    0.70
    iyev
    0.68
     Rutgers
    0.65
    iii
    0.61
    ress
    0.61
    ib
    0.61
    li
    0.60
    ii
    0.60
    ort
    0.59
     خاص
    0.58
    Act Density 0.000%

    No Known Activations