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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    射手
    -0.08
    /full
    -0.07
    George
    -0.07
    acob
    -0.07
    又是
    -0.07
    能做到
    -0.06
    文學
    -0.06
    完成
    -0.06
     taxonomy
    -0.06
    /graphql
    -0.06
    POSITIVE LOGITS
    ᗯ
    0.07
    �
    0.07
    𝗘
    0.07
     налогов
    0.07
    Ր
    0.06
    펶
    0.06
    堵
    0.06
    yyval
    0.06
    屡
    0.06
    _pushButton
    0.06
    Act Density 0.007%

    No Known Activations