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

    Neuronpedia

    INDEX
    Explanations

    diverse information sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bağlı
    -0.07
     分
    -0.07
    iol
    -0.07
    죄
    -0.07
     Expedition
    -0.06
    ergic
    -0.06
    імі
    -0.06
    utdown
    -0.06
     春
    -0.06
     завер
    -0.06
    POSITIVE LOGITS
    _VOL
    0.06
     test
    0.06
     fifth
    0.06
     тоже
    0.06
    src
    0.06
     avoided
    0.06
    /Input
    0.06
    нос
    0.06
     wsz
    0.06
     editing
    0.06
    Act Density 0.000%

    No Known Activations