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

    Neuronpedia

    INDEX
    Explanations

    image files, developing, degradation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eugene
    0.86
     McGu
    0.77
    珹
    0.77
    _<
    0.76
    ྥ
    0.76
    ᔭ
    0.75
     Razer
    0.75
    ётся
    0.74
    تنا
    0.73
     Eugen
    0.73
    POSITIVE LOGITS
    c
    0.93
    cac
    0.82
    f
    0.82
    buds
    0.73
    v
    0.73
    ad
    0.72
    ve
    0.71
    blue
    0.70
    cypress
    0.70
    ur
    0.69
    Act Density 0.001%

    No Known Activations