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

    Neuronpedia

    INDEX
    Explanations

    studying activities and foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     может
    1.05
     menace
    1.05
     může
    1.03
     чаще
    1.02
    場合があります
    1.00
     காணலாம்
    0.98
     può
    0.98
     puede
    0.96
     können
    0.96
     peuvent
    0.95
    POSITIVE LOGITS
    ה
    1.08
    ס
    0.95
    檀
    0.92
    جلس
    0.91
    했던
    0.89
     وكان
    0.89
    었고
    0.86
    ви
    0.85
    crm
    0.85
    "${
    0.84
    Act Density 0.488%

    No Known Activations