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

    Neuronpedia

    INDEX
    Explanations

    sections of text that are either completely empty or contain minimal relevant content

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

    Common internet abbreviations

    np_acts-logits-general · gemini-2.0-flash

    internet slang and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.87
    webElementXpaths
    -0.80
     AssemblyCulture
    -0.78
    StructEnd
    -0.76
    AsUp
    -0.75
     ProtoMessage
    -0.74
    Autoritní
    -0.73
    WaitGroup
    -0.72
    存于互联网档案馆
    -0.72
    UIControlState
    -0.71
    POSITIVE LOGITS
     bc
    0.57
     tbh
    0.57
     tumblr
    0.56
     @
    0.56
     fandom
    0.53
     🥺
    0.53
     idk
    0.52
     fic
    0.52
    usiai
    0.52
     /
    0.52
    Act Density 0.080%

    No Known Activations