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

    Neuronpedia

    INDEX
    Explanations

    don't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.82
    u
    0.59
    ,
    0.56
    ف
    0.54
    وس
    0.52
    ik
    0.50
    x
    0.50
    er
    0.47
     For
    0.46
    లో
    0.46
    POSITIVE LOGITS
    ن
    0.45
    ኔታ
    0.41
     мнение
    0.39
     അവര്‍
    0.39
     способность
    0.39
     दौरे
    0.39
     dolayı
    0.38
     учреждений
    0.38
    kannya
    0.37
    ท์
    0.37
    Act Density 0.324%

    No Known Activations