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

    Neuronpedia

    INDEX
    Explanations

    French characters with diacritics

    oai_token-act-pair · gemini-2.0-flash

    ©/É

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insuffisamment
    -0.66
     للمعارف
    -0.63
     Paglinawan
    -0.59
     Offisielt
    -0.58
    fromnode
    -0.58
    sizeCache
    -0.57
     nargin
    -0.57
     oprot
    -0.57
     absentee
    -0.55
     mxArray
    -0.55
    POSITIVE LOGITS
    thique
    0.60
    tudiant
    0.56
    tude
    0.55
    chapper
    0.54
    criture
    0.52
    beiter
    0.49
    charpe
    0.48
    chec
    0.48
    chapp
    0.48
    tudi
    0.47
    Act Density 0.880%

    No Known Activations