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

    Neuronpedia

    INDEX
    Explanations

    :(

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sex
    -0.07
    ('?
    -0.07
     intimacy
    -0.07
     Realty
    -0.07
     кто
    -0.06
    托
    -0.06
     Repository
    -0.06
     віль
    -0.06
    垂
    -0.06
    材
    -0.06
    POSITIVE LOGITS
    ��
    0.06
     حمل
    0.06
    ，就是
    0.06
     wouldn
    0.06
    ({
    0.06
    couldn
    0.06
    =str
    0.06
    GENER
    0.06
    [url
    0.06
    [(
    0.06
    Act Density 0.002%

    No Known Activations