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

    Neuronpedia

    INDEX
    Explanations

    lists, conjunctions, continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    0.59
    때
    0.57
    с
    0.55
    الح
    0.52
    服务端
    0.52
    ח
    0.52
    其他
    0.51
    ת
    0.51
     européen
    0.48
    ześnie
    0.47
    POSITIVE LOGITS
    romeda
    0.70
     sebagainya
    0.67
    or
    0.65
     whatnot
    0.60
    ppure
    0.60
    rews
    0.59
    ंगाबाद
    0.58
    ndash
    0.57
     secondly
    0.56
    rogens
    0.55
    Act Density 0.083%

    No Known Activations