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

    Neuronpedia

    INDEX
    Explanations

    code configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Фед
    -0.07
     fis
    -0.07
    وت
    -0.06
    Printf
    -0.06
    ish
    -0.06
    abd
    -0.06
    фт
    -0.06
     Husband
    -0.06
    bridge
    -0.06
    doesn
    -0.06
    POSITIVE LOGITS
    ‌شوند
    0.07
     ГО
    0.07
     каш
    0.06
     شوند
    0.06
     Radi
    0.06
    abilirsiniz
    0.06
     με
    0.06
     success
    0.06
     aggressively
    0.06
     disturbances
    0.06
    Act Density 0.127%

    No Known Activations