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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    z
    0.48
    comfortable
    0.41
    recognized
    0.41
    Using
    0.41
    ale
    0.40
    Down
    0.40
     concur
    0.39
     použí
    0.38
    zare
    0.38
    ´
    0.38
    POSITIVE LOGITS
     તથા
    0.51
    และการ
    0.49
    ไหม
    0.46
     rekind
    0.46
    დი
    0.46
    кци
    0.46
    기와
    0.45
     целях
    0.44
     ਅਤੇ
    0.44
     Tennyson
    0.44
    Act Density 0.002%

    No Known Activations