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

    Neuronpedia

    INDEX
    Explanations

    connective "and" followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙛
    0.73
    ों
    0.71
    ନ
    0.71
    이고
    0.68
    nya
    0.67
     browsers
    0.67
     прибыль
    0.66
    服务端
    0.65
     infar
    0.64
     МО
    0.64
    POSITIVE LOGITS
     erreichte
    0.62
    OS
    0.59
     els
    0.59
    AS
    0.59
     Truly
    0.57
     माइट
    0.57
    म्प्ट
    0.57
    داً
    0.57
    ait
    0.56
    イト
    0.56
    Act Density 0.000%

    No Known Activations