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

    Neuronpedia

    INDEX
    Explanations

    deposits terms flights submission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    说
    0.44
     başlı
    0.42
     mehr
    0.40
     pinned
    0.40
    un
    0.40
     drei
    0.40
     zwei
    0.40
     Poli
    0.40
     un
    0.39
    x
    0.39
    POSITIVE LOGITS
    िकर
    0.53
    ῇ
    0.52
    IOR
    0.49
    дать
    0.47
    водить
    0.46
     freest
    0.45
    酊
    0.45
    くなる
    0.45
    iob
    0.45
    ulfide
    0.45
    Act Density 0.000%

    No Known Activations