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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ústav
    -0.07
    ращи
    -0.06
    タイプ
    -0.06
    該
    -0.06
    aptor
    -0.06
    าคา
    -0.06
    autor
    -0.06
     接
    -0.06
     firmalar
    -0.06
    OBJECT
    -0.06
    POSITIVE LOGITS
    ,output
    0.08
    731
    0.07
     relaxing
    0.07
     date
    0.06
    a
    0.06
    -founded
    0.06
    /App
    0.06
     الأح
    0.06
    _nn
    0.06
     nová
    0.06
    Act Density 0.016%

    No Known Activations