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

    Neuronpedia

    INDEX
    Explanations

    common terms, dramatic descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    离开了
    0.46
    ino
    0.45
     Verlauf
    0.44
    ʝ
    0.43
     Pueblo
    0.43
    ul
    0.42
     Pil
    0.41
     Salem
    0.40
     Medina
    0.40
     ಮಾಡಿದ
    0.40
    POSITIVE LOGITS
    peč
    0.48
     Elkus
    0.48
    口座
    0.48
     hydride
    0.48
     tritt
    0.48
    ଞ
    0.48
     is
    0.47
    ي
    0.47
    取
    0.46
    Aaj
    0.46
    Act Density 0.000%

    No Known Activations