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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liabilities
    -0.07
     приступ
    -0.07
    ophilia
    -0.06
     Ruth
    -0.06
    ickými
    -0.06
    ох
    -0.06
     Ruby
    -0.06
     password
    -0.06
    	URL
    -0.06
     دولتی
    -0.06
    POSITIVE LOGITS
     Himal
    0.07
    (BASE
    0.07
     lack
    0.06
    ^[
    0.06
    하우
    0.06
     %@",
    0.06
    を見る
    0.06
    Franc
    0.06
    -company
    0.06
    وار
    0.06
    Act Density 0.135%

    No Known Activations