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

    Neuronpedia

    INDEX
    Explanations

    code blocks and markdown formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IntegerValue
    0.51
    %";
    0.46
    ట్స్‌మన్
    0.46
    imizin
    0.45
    strcmp
    0.45
    Aq
    0.44
    isinde
    0.43
     സഹ
    0.43
    ضمن
    0.43
    UserProg
    0.42
    POSITIVE LOGITS
    lor
    0.46
    )
    0.46
    git
    0.43
     lor
    0.43
     티
    0.42
     blade
    0.41
     মার
    0.41
     Git
    0.40
    .
    0.40
     아
    0.39
    Act Density 0.000%

    No Known Activations