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

    Neuronpedia

    INDEX
    Explanations

    references to glitches or issues related to functionality in a system

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

    glitch and loophole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Contexts
    -0.33
    GEBURTSDATUM
    -0.32
    UpdateDate
    -0.30
    MARIA
    -0.30
    fres
    -0.29
    namespaces
    -0.29
     친
    -0.29
    납
    -0.29
     algemeen
    -0.29
    fol
    -0.28
    POSITIVE LOGITS
     loophole
    0.71
     glitch
    0.61
    ChildScrollView
    0.57
     disambiguazione
    0.57
     loopholes
    0.56
    rawDesc
    0.55
    GOTREF
    0.54
     GenerationType
    0.52
    stylers
    0.52
    RTSN
    0.52
    Act Density 0.088%

    No Known Activations