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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我不是
    -0.07
    较强
    -0.07
    каз
    -0.07
    曳
    -0.07
    '.
    -0.06
    "
↵
↵
↵
    -0.06
    .IsNullOrWhiteSpace
    -0.06
    ҷ
    -0.06
    Talking
    -0.06
     [_
    -0.06
    POSITIVE LOGITS
     Quaternion
    0.07
    呤
    0.07
    _wire
    0.07
    색
    0.07
     genomic
    0.07
    ód
    0.07
     OTHERWISE
    0.06
    draul
    0.06
     Magnet
    0.06
    aled
    0.06
    Act Density 0.038%

    No Known Activations