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

    Neuronpedia

    INDEX
    Explanations

    dot

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pix
    0.80
    쟈
    0.72
    雦
    0.72
     개발
    0.68
    蜼
    0.68
     المثل
    0.66
    発展
    0.65
    墻
    0.64
     throwIfNotFound
    0.64
    ক্ষিত
    0.64
    POSITIVE LOGITS
     centrale
    0.81
     doar
    0.72
    NY
    0.69
     Drei
    0.68
     Gemeins
    0.67
     central
    0.65
    anch
    0.65
    «.
    0.63
     NY
    0.62
    central
    0.62
    Act Density 0.002%

    No Known Activations