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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     REQ
    -0.07
    (depend
    -0.07
     kẻ
    -0.07
    .xxx
    -0.07
    .review
    -0.07
     Its
    -0.07
     Some
    -0.06
     borrow
    -0.06
     sewage
    -0.06
     Computes
    -0.06
    POSITIVE LOGITS
    yalty
    0.07
    .callback
    0.07
     Bollywood
    0.06
    acebook
    0.06
    ython
    0.06
     scrolled
    0.06
    aussian
    0.06
    itored
    0.06
    MOST
    0.06
    '''↵↵
    0.06
    Act Density 0.007%

    No Known Activations