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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     YouTube
    -0.07
     chees
    -0.06
     vàng
    -0.06
    Hom
    -0.06
    .setUp
    -0.06
    seq
    -0.06
    rippling
    -0.06
     Toy
    -0.06
    grading
    -0.06
     seeds
    -0.06
    POSITIVE LOGITS
    帰
    0.07
     Infect
    0.07
     функ
    0.06
    ABB
    0.06
     ГО
    0.06
    ї
    0.06
    	INT
    0.06
    obbies
    0.06
    оп
    0.06
    HAL
    0.06
    Act Density 0.125%

    No Known Activations