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

    Neuronpedia

    INDEX
    Explanations

    torch.nn.functional as F

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    0.80
    uirre
    0.64
    γε
    0.61
    μο
    0.60
    ται
    0.58
    z
    0.58
     secundaria
    0.57
    لل
    0.57
    r
    0.57
     Salute
    0.57
    POSITIVE LOGITS
     onClose
    0.59
    ഗോ
    0.58
     onLoad
    0.56
    .
    0.56
    ล็อก
    0.55
    ロック
    0.52
    ล็
    0.52
    रोक
    0.52
     stein
    0.52
     coastline
    0.52
    Act Density 0.001%

    No Known Activations