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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _remove
    -0.06
    ад
    -0.06
    +↵
    -0.06
    icy
    -0.06
     nhiều
    -0.06
     عش
    -0.06
    んだ
    -0.06
    消费
    -0.06
    Occurred
    -0.06
    楽し
    -0.06
    POSITIVE LOGITS
     началь
    0.07
     поможет
    0.06
    ินทาง
    0.06
     inici
    0.06
    enter
    0.06
     lah
    0.06
     Franti
    0.06
    母亲
    0.06
    Outlet
    0.06
    .Env
    0.06
    Act Density 0.011%

    No Known Activations