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

    Neuronpedia

    INDEX
    Explanations

    look forper lotloved for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жи
    0.51
    ти
    0.50
    сти
    0.46
    ani
    0.44
    зи
    0.44
    ван
    0.42
    kében
    0.42
    пи
    0.42
    ни
    0.41
    щая
    0.41
    POSITIVE LOGITS
     mit
    0.40
     de
    0.40
     kombin
    0.40
     prom
    0.39
     yang
    0.39
     pares
    0.38
     te
    0.38
     menggunakan
    0.38
     cest
    0.38
     des
    0.37
    Act Density 0.065%

    No Known Activations