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

    Neuronpedia

    INDEX
    Explanations

    phrases that note or describe mathematical expressions and their definitions

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

    reads equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.65
     kasarigan
    -0.64
    $_['
    -0.60
    IBOutlet
    -0.58
    Попис
    -0.57
    StoryboardSegue
    -0.57
    istoitu
    -0.56
    extAlignment
    -0.56
     ligiloj
    -0.56
    Rüyada
    -0.56
    POSITIVE LOGITS
     CURIAM
    0.37
     meaning
    0.32
    Meaning
    0.32
     Meaning
    0.32
    :
    0.31
     CONT
    0.30
    点了点头
    0.29
     Pop
    0.29
    地说
    0.29
    CrossRef
    0.29
    Act Density 0.252%

    No Known Activations