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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    낸
    -0.07
    Visibility
    -0.07
    _SPEED
    -0.07
    ूड
    -0.07
    Removing
    -0.07
    bec
    -0.06
    "/><
    -0.06
    uden
    -0.06
     مانند
    -0.06
     vysvět
    -0.06
    POSITIVE LOGITS
     expressive
    0.06
    /'.
    0.06
     trabal
    0.06
     출장
    0.06
     صف
    0.06
    .Some
    0.06
     murky
    0.06
     aston
    0.06
     Jam
    0.06
     ad
    0.06
    Act Density 0.021%

    No Known Activations