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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to negation and clarification

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

    because of that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.41
    schirm
    -0.41
    Tikang
    -0.38
    FormTagHelper
    -0.38
    FACTS
    -0.38
     مرئيه
    -0.36
     FACTS
    -0.36
     Waray
    -0.36
    Après
    -0.35
    AnchorTagHelper
    -0.35
    POSITIVE LOGITS
     själva
    0.47
    IUrlHelper
    0.44
    jsonwebtoken
    0.43
     actual
    0.40
    +#+#
    0.40
    OrNil
    0.39
    MessageState
    0.39
     directly
    0.38
     createSprite
    0.38
     direct
    0.38
    Act Density 0.202%

    No Known Activations