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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lix
    -0.06
     rdr
    -0.06
    suz
    -0.06
    ющей
    -0.06
     advisory
    -0.06
    brids
    -0.06
    adapter
    -0.06
    tion
    -0.06
    rc
    -0.06
    OU
    -0.06
    POSITIVE LOGITS
    м
    0.07
     карт
    0.07
    <F
    0.07
    すべて
    0.07
     남
    0.07
     Каб
    0.06
     seb
    0.06
     Talking
    0.06
     gaat
    0.06
     jeopard
    0.06
    Act Density 0.048%

    No Known Activations