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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cal
    -0.08
    幸好
    -0.08
    cdf
    -0.07
    stype
    -0.07
    sealed
    -0.07
     Backend
    -0.07
    شارك
    -0.07
    .folder
    -0.07
     Upload
    -0.07
     Drew
    -0.07
    POSITIVE LOGITS
     videoer
    0.08
    unders
    0.08
    の一
    0.07
    קר
    0.06
    윔
    0.06
    아버
    0.06
    ミ
    0.06
    iers
    0.06
    酒
    0.06
     이용
    0.06
    Act Density 0.014%

    No Known Activations