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

    Neuronpedia

    INDEX
    Explanations

    handles / responsible for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    첫
    0.46
    ያንዳንዱ
    0.45
    StatusOK
    0.45
     시간이
    0.44
     عدم
    0.44
     badass
    0.43
     같이
    0.43
     방식으로
    0.43
     게시
    0.43
    폭
    0.43
    POSITIVE LOGITS
     Apprentice
    0.50
    t
    0.50
    i
    0.48
    u
    0.47
     Reliable
    0.47
    ’
    0.47
     Connection
    0.47
     Apprentices
    0.46
     Cement
    0.46
     Pies
    0.46
    Act Density 0.001%

    No Known Activations