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

    Neuronpedia

    INDEX
    Explanations

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🔜
    1.09
     portug
    1.08
     datas
    1.06
     firefox
    1.05
     alice
    1.05
     데이터
    1.02
     layanan
    1.02
     bmw
    1.01
     캠
    1.00
    🗯
    0.99
    POSITIVE LOGITS
    Untitled
    0.88
    untitled
    0.77
    Unnamed
    0.69
    diethyl
    0.67
    NaN
    0.66
    Difference
    0.64
    ↵
    0.64
    Create
    0.63
    Раз
    0.62
    Problem
    0.60
    Act Density 0.227%

    No Known Activations