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

    Neuronpedia

    INDEX
    Explanations

    personal profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etyl
    -0.07
     pd
    -0.07
     Maiden
    -0.07
    743
    -0.06
     curious
    -0.06
    again
    -0.06
    _rgb
    -0.06
     Cu
    -0.06
    يد
    -0.06
    Ù
    -0.06
    POSITIVE LOGITS
    ่างประเทศ
    0.06
    */↵
    0.06
     apost
    0.06
     ah
    0.06
    geme
    0.06
    .HTML
    0.06
     */↵↵↵
    0.06
     скры
    0.06
     tether
    0.06
     generals
    0.06
    Act Density 0.013%

    No Known Activations