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

    Neuronpedia

    INDEX
    Explanations

    exposure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    美國
    -0.08
    _POP
    -0.07
    ingle
    -0.06
     تعد
    -0.06
     صح
    -0.06
     سرعت
    -0.06
     승
    -0.06
    ='
    -0.06
    عاد
    -0.06
     ضمن
    -0.06
    POSITIVE LOGITS
    -Петерб
    0.06
    0.06
    jectives
    0.06
     Прав
    0.06
    series
    0.06
    agher
    0.06
     gest
    0.06
     Bbw
    0.06
     accounted
    0.06
    ฎ
    0.05
    Act Density 0.079%

    No Known Activations