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

    Neuronpedia

    INDEX
    Explanations

    Intel and its business

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =
    0.62
     municipales
    0.62
    las
    0.61
    ara
    0.60
     políticas
    0.60
     Италия
    0.59
    industrie
    0.59
    k
    0.59
    ]).
    0.58
    ляция
    0.58
    POSITIVE LOGITS
     effectu
    0.64
    ANSAS
    0.63
     scriptures
    0.59
    বিধা
    0.59
     princess
    0.58
    ש
    0.57
     blossom
    0.55
    नं
    0.55
     toolPath
    0.54
    ய்
    0.54
    Act Density 0.008%

    No Known Activations