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

    Neuronpedia

    INDEX
    Explanations

    mathematical/statistical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xor
    -0.09
    国内
    -0.08
    阅
    -0.08
     三国
    -0.08
    国家
    -0.08
    网友
    -0.08
     JVM
    -0.08
     cnt
    -0.08
     Byzantine
    -0.07
     considerably
    -0.07
    POSITIVE LOGITS
     dashed
    0.09
    Units
    0.09
    .Convert
    0.09
    Incorrect
    0.08
     Regents
    0.08
     완료
    0.08
    _units
    0.08
     incorrectly
    0.08
     passo
    0.08
     Schritte
    0.08
    Act Density 0.132%

    No Known Activations