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

    Neuronpedia

    INDEX
    Explanations

    text formatting and styles involving underlines

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

    underline in structured notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Slf
    -0.40
     ester
    -0.34
    ActionResult
    -0.32
     espir
    -0.30
     €€
    -0.29
    AnimationsModule
    -0.28
    Có
    -0.28
    irr
    -0.28
     grains
    -0.28
    Odour
    -0.28
    POSITIVE LOGITS
    underline
    0.72
    adaptiveStyles
    0.64
     Administrativna
    0.63
    OGND
    0.59
     nonUne
    0.59
    Underline
    0.56
     المعيارى
    0.56
     kasarigan
    0.55
     ProtoMessage
    0.54
    DIPSETTING
    0.54
    Act Density 0.456%

    No Known Activations