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

    Neuronpedia

    INDEX
    Explanations

    conversion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    specs
    -0.08
    716
    -0.06
     fists
    -0.06
    кул
    -0.06
     Salad
    -0.06
    crypt
    -0.06
     proletariat
    -0.06
    ная
    -0.06
     patents
    -0.06
    674
    -0.06
    POSITIVE LOGITS
     Conversion
    0.06
     sécur
    0.06
    ıntı
    0.06
    -y
    0.06
     "/"↵
    0.06
    だって
    0.06
     succes
    0.06
    Cantidad
    0.06
     DACA
    0.06
    (nombre
    0.06
    Act Density 0.005%

    No Known Activations