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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GG
    -0.07
     uyar
    -0.07
     tuz
    -0.06
    dbe
    -0.06
     공고
    -0.06
    .Callback
    -0.06
    ‌گ
    -0.06
     Серед
    -0.06
    levance
    -0.06
     Hilfe
    -0.06
    POSITIVE LOGITS
    ืน
    0.07
     sanitary
    0.07
     murdering
    0.07
     Air
    0.07
     Motor
    0.06
    俄
    0.06
     naval
    0.06
    named
    0.06
    ůst
    0.06
    "]=>
    0.06
    Act Density 0.021%

    No Known Activations