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

    Neuronpedia

    INDEX
    Explanations

    future of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ні
    1.90
    ма
    1.76
    Issledovatel
    1.73
    <%=
    1.73
    ર
    1.72
    ни
    1.66
    ный
    1.64
    <?=
    1.63
    ط
    1.63
    со
    1.63
    POSITIVE LOGITS
    ו
    1.79
    azione
    1.56
     awhile
    1.56
    しばらく
    1.54
    eyn
    1.53
    cion
    1.52
    도를
    1.52
    ä
    1.51
     whence
    1.50
    に
    1.49
    Act Density 0.018%

    No Known Activations