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

    Neuronpedia

    INDEX
    Explanations

    implementations complexityscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wedstrijd
    0.95
     adição
    0.86
     luta
    0.85
    profissional
    0.85
    iya
    0.82
     física
    0.82
     iguais
    0.82
    ubwa
    0.82
     насыщен
    0.82
     neler
    0.81
    POSITIVE LOGITS
     Okanagan
    0.70
     compressible
    0.68
     Sigmund
    0.67
     Because
    0.66
     Easier
    0.66
     Egypt
    0.66
    ۔۔
    0.64
     Cats
    0.64
    ↵↵
    0.63
     My
    0.63
    Act Density 0.000%

    No Known Activations