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

    Neuronpedia

    INDEX
    Explanations

    closing title tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قو
    0.66
    dub
    0.64
    nością
    0.59
    receive
    0.59
    تو
    0.58
     پری
    0.58
    Receive
    0.58
    anco
    0.56
    enstein
    0.56
    s
    0.56
    POSITIVE LOGITS
    散射
    0.78
     తరువాత
    0.77
     Sessions
    0.75
     unbiased
    0.75
    clips
    0.75
     ಗಮನ
    0.73
     topic
    0.73
     అనంతరం
    0.73
    瞟
    0.72
     lỗi
    0.72
    Act Density 0.020%

    No Known Activations