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

    Neuronpedia

    INDEX
    Explanations

    Fiction story snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谢邀
    -0.07
     الإمام
    -0.07
     الأمير
    -0.07
    很长时间
    -0.07
    _pi
    -0.07
    _K
    -0.06
     Exterior
    -0.06
    เทศกาล
    -0.06
    只不过是
    -0.06
     thơ
    -0.06
    POSITIVE LOGITS
    .bind
    0.07
    ington
    0.07
    _DOWN
    0.07
    $_
    0.06
    se
    0.06
     NJ
    0.06
    英语
    0.06
    wróci
    0.06
    -establish
    0.06
    _CNT
    0.06
    Act Density 0.108%

    No Known Activations