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

    Neuronpedia

    INDEX
    Explanations

    Pulp Fiction, movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    平方米
    -0.09
    阵
    -0.08
    Sinh
    -0.08
    TECT
    -0.08
    /forms
    -0.08
    小时
    -0.08
     comprender
    -0.08
     formulario
    -0.07
    Sq
    -0.07
     discern
    -0.07
    POSITIVE LOGITS
     barbecue
    0.09
     violence
    0.09
     Knife
    0.08
     swapped
    0.08
     മരിച്ചു
    0.08
     bloody
    0.08
     deadly
    0.08
     flavorful
    0.08
     swapping
    0.08
     ഒഴ
    0.08
    Act Density 0.003%

    No Known Activations