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

    Neuronpedia

    INDEX
    Explanations

    code syntax with angle brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    聽
    0.70
    reon
    0.69
    ‍
    0.69
    ؒ
    0.67
    ‍ह
    0.66
     elytris
    0.66
    rrbracket
    0.66
     Oyster
    0.64
    <unused749>
    0.64
     XXL
    0.63
    POSITIVE LOGITS
     <
    5.03
    <
    4.75
     `<
    3.69
    .<
    3.52
     $<
    3.49
     "<
    3.44
    ,<
    3.43
     '<
    3.41
    -<
    3.39
    。<
    3.30
    Act Density 0.412%

    No Known Activations