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

    Neuronpedia

    INDEX
    Explanations

    require('express')

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.77
    1
    0.70
     in
    0.68
     heures
    0.65
    ن
    0.64
    ام
    0.63
    কে
    0.61
    é
    0.61
    وا
    0.61
    ست
    0.60
    POSITIVE LOGITS
    뇰
    0.54
    s
    0.53
    aroos
    0.50
    osevelt
    0.49
     speciali
    0.49
    Comparer
    0.48
    rVert
    0.48
    ดิ
    0.48
     wildly
    0.48
     sparsebundle
    0.48
    Act Density 0.000%

    No Known Activations