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

    Neuronpedia

    INDEX
    Explanations

    terms related to imperfections and flaws

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

    impartial judiciary, superficial lesions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.57
    Hentet
    -0.55
    RenderAtEndOf
    -0.54
     StatefulWidget
    -0.53
     Lijst
    -0.52
     ſtate
    -0.50
    躇
    -0.50
    useNewUrlParser
    -0.49
     whoſe
    -0.49
    pantalón
    -0.49
    POSITIVE LOGITS
     imperfections
    1.41
     imperfection
    1.38
     imperfect
    1.31
     imperf
    1.16
     Imper
    1.11
    Imper
    1.02
     imperfectly
    0.98
     IMPER
    0.71
    imper
    0.53
     Imperium
    0.48
    Act Density 0.013%

    No Known Activations