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

    Neuronpedia

    INDEX
    Explanations

    travel log of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    0.62
     unsubstituted
    0.59
    es
    0.56
    i
    0.56
     o
    0.55
    נ
    0.55
     otor
    0.54
    1
    0.54
    י
    0.54
    ку
    0.54
    POSITIVE LOGITS
     لیکن
    0.54
    秥
    0.53
     डि
    0.52
     الأد
    0.52
    漂
    0.51
    എന്ന
    0.50
    孩子的
    0.49
     بلکه
    0.49
     ලැබ
    0.48
     عزیز
    0.48
    Act Density 0.000%

    No Known Activations