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

    Neuronpedia

    INDEX
    Explanations

    staff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    부터
    1.19
    ਰ
    1.08
    인
    1.07
     Amusement
    1.00
    주
    0.99
     Р
    0.98
    ש
    0.98
    ्यू
    0.96
    ット
    0.95
     basso
    0.95
    POSITIVE LOGITS
    ありません
    1.57
     endonuclease
    1.09
     acepta
    1.07
    кость
    1.05
     enviar
    1.03
    😊
    1.03
    ्मी
    1.02
    yyyy
    1.00
    اا
    1.00
    了一个
    1.00
    Act Density 0.000%

    No Known Activations