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

    Neuronpedia

    INDEX
    Explanations

    non-latin script elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ujjati
    1.21
    getRedTeam
    1.20
     Государ
    1.14
     Україн
    1.13
    ène
    1.12
     ಲಕ್ಷ
    1.10
     กํา
    1.08
     interstitiis
    1.08
     silam
    1.08
     ರಿಂದ
    1.07
    POSITIVE LOGITS
    즈
    1.06
    斯
    1.02
    在
    0.91
    ＝
    0.86
    스
    0.84
    許
    0.80
    카
    0.80
    比
    0.77
     아이
    0.76
    스를
    0.73
    Act Density 0.058%

    No Known Activations