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

    Neuronpedia

    INDEX
    Explanations

    partial derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.52
    Y
    0.51
    ↵
    0.50
    ,
    0.48
    V
    0.46
    From
    0.45
    ;
    0.44
    。
    0.43
    /
    0.43
    y
    0.43
    POSITIVE LOGITS
     Новосибир
    0.50
     स्नात
    0.48
    𒆜
    0.47
     ഗവേഷ
    0.46
    actifs
    0.45
    皙
    0.45
     Стаўкі
    0.45
     පෙ
    0.44
     기업
    0.43
    သိ
    0.43
    Act Density 0.025%

    No Known Activations