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

    Neuronpedia

    INDEX
    Explanations

    dressing modestly, other genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.56
    ت
    0.54
     Obsidian
    0.50
    ي
    0.48
    i
    0.48
    oc
    0.47
    is
    0.47
     for
    0.46
     premières
    0.46
    خ
    0.45
    POSITIVE LOGITS
     اندراج
    0.55
     लक्ष
    0.51
    лянчук
    0.51
     Лит
    0.51
     зуб
    0.50
     有限
    0.50
     нагру
    0.49
     yüzy
    0.49
     drob
    0.49
     очередь
    0.48
    Act Density 0.000%

    No Known Activations