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
    Fetcher
    -0.07
    advert
    -0.07
     Siemens
    -0.07
    ㎞
    -0.07
     Validates
    -0.07
    <Cell
    -0.07
    Ņ
    -0.07
    /Game
    -0.07
     FUCK
    -0.07
    .YES
    -0.07
    POSITIVE LOGITS
    อง
    0.07
     boring
    0.06
    מתח
    0.06
    申请人
    0.06
     becoming
    0.06
    我们在
    0.06
     minimize
    0.06
     hill
    0.06
    [w
    0.06
     integr
    0.06
    Act Density 0.002%

    No Known Activations