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

    Neuronpedia

    INDEX
    Explanations

    printf "%

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ঁয়
    0.44
    निश्
    0.44
    ),]$
    0.43
     შეგიძლიათ
    0.42
    缛
    0.41
     আহমেদ
    0.40
     Miocene
    0.40
    䔬
    0.40
     Deloitte
    0.39
    स्टिक
    0.39
    POSITIVE LOGITS
    ld
    0.70
    lld
    0.69
     ld
    0.64
    lf
    0.63
    zu
    0.60
     ",
    0.54
    ll
    0.53
    hd
    0.53
    d
    0.51
    %,
    0.51
    Act Density 0.004%

    No Known Activations