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

    Neuronpedia

    INDEX
    Explanations

    error message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अंकों
    0.64
    દાન
    0.63
    Br
    0.63
    канчи
    0.60
    ക്കിയി
    0.59
    Hasta
    0.59
    済み
    0.58
    ಸ
    0.58
    合わせて
    0.57
     Mathew
    0.57
    POSITIVE LOGITS
     arise
    3.11
     arises
    3.06
     arose
    2.82
     occur
    2.72
     arisen
    2.69
     occurs
    2.56
     arising
    2.55
    เกิดขึ้น
    2.50
     occurred
    2.50
     emerge
    2.49
    Act Density 0.485%

    No Known Activations