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

    Neuronpedia

    INDEX
    Explanations

    python, r, latex code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Employer
    0.71
     is
    0.68
    ник
    0.66
     அடையாளம்
    0.64
    ليك
    0.64
    يل
    0.63
    лик
    0.63
     dajj
    0.62
     informações
    0.61
    ਾਰੇ
    0.60
    POSITIVE LOGITS
     and
    0.74
    и
    0.73
    .
    0.70
    ও
    0.70
     কথাও
    0.69
     also
    0.66
    도
    0.66
    -
    0.65
    5
    0.64
    P
    0.63
    Act Density 0.032%

    No Known Activations