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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speculation and evaluation in various contexts

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

    roles, actions, and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RTEX
    -0.56
    tagext
    -0.44
    AnchorStyles
    -0.41
    parsedMessage
    -0.40
     disponibilités
    -0.39
    ConstraintLayout
    -0.39
    InjectAttribute
    -0.38
    헌
    -0.38
    lequin
    -0.38
    tableFuture
    -0.38
    POSITIVE LOGITS
     themselves
    0.44
     незавершена
    0.44
     contextLoads
    0.43
    __":
    0.43
     TAMBÉM
    0.43
    themselves
    0.42
    تقاوى
    0.41
     själva
    0.41
     kasarigan
    0.41
    теристики
    0.41
    Act Density 0.072%

    No Known Activations