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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spiele
    -0.08
    ﲻ
    -0.08
    TexImage
    -0.07
    chapter
    -0.07
    Culture
    -0.07
    뉩
    -0.07
    _pet
    -0.07
    弇
    -0.07
     kö
    -0.06
     Ülke
    -0.06
    POSITIVE LOGITS
    ทาง
    0.07
    *',
    0.07
    AWN
    0.07
    ';↵↵
    0.07
    �
    0.06
     Flag
    0.06
    躺
    0.06
    ropolitan
    0.06
     ATH
    0.06
     CPU
    0.06
    Act Density 0.065%

    No Known Activations