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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to verification and validation processes

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

    Two-letter capitalized abbreviations

    np_acts-logits-general · gemini-2.0-flash

    chocolates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
     дописавши
    -0.71
     OFDb
    -0.70
     NSCoder
    -0.69
     intptr
    -0.67
     himo
    -0.67
     protoimpl
    -0.65
     Baillargeon
    -0.64
    TypedDataSet
    -0.64
    tagHelperRunner
    -0.62
    POSITIVE LOGITS
    as
    0.51
    rawtypes
    0.48
     Hist
    0.47
    polate
    0.47
    ita
    0.47
    createComponent
    0.47
    ę
    0.47
    qa
    0.45
    ReadByte
    0.44
    lietta
    0.43
    Act Density 0.254%

    No Known Activations