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

    Neuronpedia

    INDEX
    Explanations

    numbers or quantities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oksid
    0.57
     sapon
    0.54
     descriptors
    0.54
     არს
    0.54
     geodes
    0.53
    िब
    0.53
     axi
    0.53
     oxidizing
    0.53
    差別
    0.52
    क्रमण
    0.52
    POSITIVE LOGITS
    最初は
    0.56
    とりあえず
    0.56
     lentamente
    0.55
    まだまだ
    0.54
     још
    0.54
    メール
    0.54
    是以
    0.54
    uttaa
    0.54
     from
    0.53
    暇
    0.53
    Act Density 0.000%

    No Known Activations