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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মো
    0.44
     médica
    0.44
     ficou
    0.43
     caiu
    0.42
    ଗ
    0.41
     abogado
    0.40
     abogados
    0.39
     voglia
    0.39
     acero
    0.39
    أ
    0.39
    POSITIVE LOGITS
    zoek
    0.44
     multiuser
    0.42
     unknown
    0.40
    nese
    0.40
    frage
    0.40
    ./
    0.39
     대상으로
    0.39
     나와
    0.39
    twig
    0.39
    chid
    0.39
    Act Density 0.002%

    No Known Activations