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

    Neuronpedia

    INDEX
    Explanations

    codes or expressions related to data values, particularly in a programming or computational context

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

    numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers between 0 and 255

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.67
     rate
    -0.61
    mybatisplus
    -0.58
    tanleria
    -0.57
     tasa
    -0.56
    Rate
    -0.55
     Ganga
    -0.54
    lehnt
    -0.54
    Carriera
    -0.54
    艸
    -0.53
    POSITIVE LOGITS
    FunctionFlags
    0.57
    CodeAttribute
    0.53
    #
    0.48
    Mediabestanden
    0.46
    
    0.46
    vää
    0.45
    sizeCache
    0.45
     Katal
    0.45
     gynnwys
    0.43
    croll
    0.43
    Act Density 0.209%

    No Known Activations