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

    Neuronpedia

    INDEX
    Explanations

    go

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ولت
    0.68
     escalator
    0.61
    지가
    0.60
     βασ
    0.60
     আন্দোলন
    0.59
    离
    0.59
     som
    0.58
    জমেন্ট
    0.58
     Hora
    0.57
    Har
    0.57
    POSITIVE LOGITS
     ahead
    4.71
     Ahead
    4.21
    ahead
    3.95
    Ahead
    3.89
    переди
    1.68
     앞
    1.68
     вперед
    1.67
     delante
    1.64
     davanti
    1.64
     پیش
    1.58
    Act Density 0.006%

    No Known Activations