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

    Neuronpedia

    INDEX
    Explanations

    questions and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    -2.52
     has
    -2.47
     to
    -2.47
     is
    -2.36
    ↑↑↑</
    -2.33
    !
    -2.19
     
    -2.13
     (
    -2.03
     D
    -1.95
     does
    -1.95
    POSITIVE LOGITS
    盌
    3.08
    2
    3.03
     插画
    2.58
    媖
    2.58
    ꨄ
    2.52
    傒
    2.50
    8
    2.48
    ჻
    2.48
     jepang
    2.45
    4
    2.45
    Act Density 0.001%

    No Known Activations