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

    Neuronpedia

    INDEX
    Explanations

    Web search results summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سنت
    -0.06
    Meg
    -0.06
    뮤
    -0.06
     allerg
    -0.06
     �
    -0.06
    ounding
    -0.06
    ircular
    -0.06
    取り
    -0.06
    xaa
    -0.06
    igeria
    -0.06
    POSITIVE LOGITS
    리는
    0.07
    pecified
    0.06
     giàu
    0.06
    _TMP
    0.06
    推荐
    0.06
    447
    0.06
     dome
    0.06
    家的
    0.06
    兒
    0.06
     жиз
    0.06
    Act Density 0.001%

    No Known Activations