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

    Neuronpedia

    INDEX
    Explanations

    ju

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    research
    -0.08
    ammed
    -0.08
    _barang
    -0.07
    iks
    -0.07
    ONA
    -0.06
     Ones
    -0.06
    센
    -0.06
     EACH
    -0.06
     Graz
    -0.06
    erken
    -0.06
    POSITIVE LOGITS
     rau
    0.07
     Engl
    0.07
     deadly
    0.06
     جر
    0.06
     relied
    0.06
    يكي
    0.06
     chiff
    0.06
    delimiter
    0.06
     */
↵
    0.06
    jur
    0.06
    Act Density 0.001%

    No Known Activations