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

    Neuronpedia

    INDEX
    Explanations

    covering topics or aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उड़ा
    0.58
    ことができる
    0.58
     высокая
    0.58
    ı
    0.58
     آمریکا
    0.57
     Aś
    0.57
     особен
    0.57
    。",
    0.57
    ছাড়া
    0.57
     arma
    0.56
    POSITIVE LOGITS
     covered
    0.82
    Cover
    0.73
    h
    0.69
    covered
    0.68
    i
    0.68
    in
    0.65
     covers
    0.64
    :
    0.63
     covering
    0.63
     покры
    0.62
    Act Density 0.066%

    No Known Activations