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

    Neuronpedia

    INDEX
    Explanations

    stopping and exiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    каў
    0.85
    到的
    0.77
    फाइनल
    0.75
    ölker
    0.73
    Զ
    0.72
    ERS
    0.71
     puissance
    0.69
    ল
    0.69
    的值
    0.69
     kennis
    0.68
    POSITIVE LOGITS
     gracefully
    0.83
     abruptly
    0.76
    討論
    0.73
     summarizes
    0.72
    setTimeout
    0.69
     khỏi
    0.68
     realizing
    0.67
     unconditionally
    0.67
    imb
    0.66
     제출
    0.66
    Act Density 0.216%

    No Known Activations