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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers or coordinates followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    numbers, commas, and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =-\
    -1.06
    =-\
    -0.99
    ,-\
    -0.97
    $-\
    -0.94
    negative
    -0.93
    (-\
    -0.92
     $-\
    -0.92
    )=-\
    -0.91
     negative
    -0.91
     Negative
    -0.87
    POSITIVE LOGITS
    styleable
    0.53
     समीक्षाओं
    0.47
    writeFieldEnd
    0.46
    resave
    0.45
    EDEFAULT
    0.44
    lename
    0.42
    enterOuterAlt
    0.42
    ஈ
    0.41
    თ
    0.41
    ImageContext
    0.40
    Act Density 0.767%

    No Known Activations