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

    Neuronpedia

    INDEX
    Explanations

    explain why

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不同
    -0.08
    股份
    -0.07
     University
    -0.07
    股权
    -0.07
     np
    -0.07
    ynn
    -0.06
    verständ
    -0.06
    谠
    -0.06
    吭
    -0.06
    David
    -0.06
    POSITIVE LOGITS
     Suicide
    0.07
    丧失
    0.07
    �
    0.07
    량
    0.07
    ⠇
    0.06
     supporters
    0.06
    _alive
    0.06
    ヵ
    0.06
    ケ
    0.06
     forcibly
    0.06
    Act Density 0.003%

    No Known Activations