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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.71
    <eos>
    -0.65
    ↵
    -0.58
    ↵↵↵
    -0.48
    '
    -0.44
    なのです
    -0.42
    .
    -0.42
    ’
    -0.41
    !
    -0.38
    사
    -0.38
    POSITIVE LOGITS
    IsContent
    1.11
     NSCoder
    1.01
     snippetHide
    1.00
    GraphicsUnit
    0.99
    mybatisplus
    0.95
     myſelf
    0.90
    ftagPool
    0.88
    awtextra
    0.84
    migrationBuilder
    0.83
     Efq
    0.83
    Act Density 0.003%

    No Known Activations