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

    Neuronpedia

    INDEX
    Explanations

    Jac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وان
    -0.07
    ewriter
    -0.07
     surprise
    -0.07
     invention
    -0.07
    osterone
    -0.07
     obedient
    -0.06
    _PACKAGE
    -0.06
     Connecting
    -0.06
    debug
    -0.06
    088
    -0.06
    POSITIVE LOGITS
    .CommandType
    0.07
    ibling
    0.07
     NC
    0.06
     آنلاین
    0.06
    .output
    0.06
    ()?>
    0.06
    зано
    0.06
     Москва
    0.06
    ُن
    0.06
    kat
    0.06
    Act Density 0.002%

    No Known Activations