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

    Neuronpedia

    INDEX
    Explanations

    Lying and truth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appeared
    -0.06
    }
↵
↵
↵
    -0.06
    hti
    -0.06
    ूड
    -0.06
     monk
    -0.06
     suger
    -0.06
    吾
    -0.06
    659
    -0.06
    ()])↵
    -0.06
    .readlines
    -0.06
    POSITIVE LOGITS
    Charts
    0.06
    vably
    0.06
     excerpts
    0.06
    image
    0.06
    дрес
    0.06
    _PARTITION
    0.06
    랍니다
    0.06
     inj
    0.06
     пів
    0.06
    Bet
    0.06
    Act Density 0.045%

    No Known Activations