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

    Neuronpedia

    INDEX
    Explanations

    AI disclaimers about advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সক্রিয়
    0.34
     voller
    0.31
     considérable
    0.31
     ശരീര
    0.30
    CHCl
    0.30
    겠습니다
    0.29
     সক্রিয়
    0.28
    Hare
    0.28
     drawRight
    0.28
    州市
    0.28
    POSITIVE LOGITS
    бан
    0.36
    info
    0.35
    あくまで
    0.34
    FAQ
    0.34
    port
    0.33
    ிக
    0.32
     afar
    0.32
    appen
    0.31
     FAQ
    0.31
     misinformation
    0.31
    Act Density 0.067%

    No Known Activations