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

    Neuronpedia

    INDEX
    Explanations

    quite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creditor
    -0.07
     analsex
    -0.07
     sacks
    -0.07
     accountable
    -0.07
    Eu
    -0.06
    -R
    -0.06
     AFTER
    -0.06
    .findById
    -0.06
    _AUTHOR
    -0.06
     나를
    -0.06
    POSITIVE LOGITS
    ２
    0.06
    공지
    0.06
    (gl
    0.06
     모르
    0.06
    averse
    0.06
    bands
    0.06
    thane
    0.06
    Ghost
    0.06
    _logger
    0.06
     göz
    0.06
    Act Density 0.003%

    No Known Activations