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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ▷
    -0.07
     urges
    -0.07
    amas
    -0.07
    乡村
    -0.07
     navigate
    -0.07
     tl
    -0.07
     Kinder
    -0.07
    load
    -0.07
    ݥ
    -0.07
     bin
    -0.07
    POSITIVE LOGITS
    (pa
    0.09
    と思って
    0.08
    -sp
    0.08
    пп
    0.07
    较为
    0.07
    )||(
    0.07
     Ci
    0.07
    .getDay
    0.07
     leuk
    0.07
     reint
    0.06
    Act Density 0.001%

    No Known Activations