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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic events and research papers

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

    academic working papers and talks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onReady
    -0.32
     reta
    -0.32
     preparation
    -0.30
    oplasma
    -0.30
     dro
    -0.29
    levelse
    -0.29
     Scene
    -0.29
     Poco
    -0.29
    phrine
    -0.28
    msgSender
    -0.28
    POSITIVE LOGITS
     MainAxisSize
    0.84
     Numerade
    0.75
    GEBURTSDATUM
    0.71
     mergeFrom
    0.62
    0.60
    IntoConstraints
    0.59
    ConstraintMaker
    0.58
     EconPapers
    0.57
    AddTagHelper
    0.57
    expandindo
    0.56
    Act Density 0.330%

    No Known Activations