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

    Neuronpedia

    INDEX
    Explanations

    a or b after slash or comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     التح
    0.79
     alternativ
    0.73
    ⠀⠀⠀⠀
    0.71
    ../../
    0.70
    สำ
    0.66
     สำ
    0.65
     بهذه
    0.64
     الت
    0.63
    เพียง
    0.63
    好評
    0.62
    POSITIVE LOGITS
     A
    1.82
     X
    1.71
     B
    1.55
     x
    1.37
     N
    1.31
     Q
    1.30
     C
    1.29
    A
    1.28
     S
    1.27
     M
    1.26
    Act Density 1.120%

    No Known Activations