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

    Neuronpedia

    INDEX
    Explanations

    programming, numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ئ
    0.64
     Srivastava
    0.64
     Mistakes
    0.63
     ошибка
    0.59
     infix
    0.58
     Huffman
    0.58
     weren
    0.57
    瘧
    0.57
     '\
    0.57
     Fehler
    0.57
    POSITIVE LOGITS
    UserState
    0.63
    İR
    0.62
    Clr
    0.62
    గో
    0.62
    矫
    0.62
    IF
    0.61
     నాయ
    0.60
    IDC
    0.60
    oning
    0.59
    ΙΚ
    0.59
    Act Density 0.000%

    No Known Activations