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

    Neuronpedia

    INDEX
    Explanations

    ne words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.91
    ات
    1.57
    с
    1.49
    ก
    1.47
    er
    1.42
    at
    1.41
    ن
    1.41
    ز
    1.39
    ul
    1.38
    ر
    1.36
    POSITIVE LOGITS
     senjata
    1.02
     alcanz
    1.01
     richiede
    1.01
     данни
    0.98
     milhões
    0.97
    čnog
    0.97
    後に
    0.96
     públicas
    0.96
     доступны
    0.93
     recib
    0.92
    Act Density 0.000%

    No Known Activations