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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    灵气
    -0.06
    疾
    -0.06
    .Filter
    -0.06
     Apt
    -0.06
    PLUS
    -0.06
    getText
    -0.06
    pez
    -0.06
    핌
    -0.06
    touches
    -0.06
    unter
    -0.06
    POSITIVE LOGITS
    _documents
    0.07
    電話
    0.07
     games
    0.07
     литератур
    0.07
     iliş
    0.07
     것이
    0.06
    Overlay
    0.06
    莫名其妙
    0.06
    влекательн
    0.06
    rów
    0.06
    Act Density 0.002%

    No Known Activations