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
    인
    -0.07
    IRCLE
    -0.06
    .base
    -0.06
     inappropriate
    -0.06
     Bachelor
    -0.06
     vulgar
    -0.06
     Conse
    -0.06
     léka
    -0.06
     foregoing
    -0.05
    anglicky
    -0.05
    POSITIVE LOGITS
    _nav
    0.07
    ++){
    0.07
     lid
    0.07
    ...)
    0.06
    (delete
    0.06
    >{↵
    0.06
     hashing
    0.06
    είου
    0.06
     opráv
    0.06
     BusinessException
    0.06
    Act Density 0.002%

    No Known Activations