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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals or articles

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

    journal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.63
     confort
    -0.58
    graphiques
    -0.56
     Conſ
    -0.55
     Anſ
    -0.54
    Stret
    -0.54
    reactstrap
    -0.52
    ſelf
    -0.52
     Perſ
    -0.52
     surla
    -0.51
    POSITIVE LOGITS
    enumi
    0.45
     emails
    0.40
     Emails
    0.36
     AssemblyCulture
    0.35
    EnableWeb
    0.33
     StatefulWidget
    0.33
    Портал
    0.33
    ISupport
    0.32
     joaat
    0.32
    ConstraintMaker
    0.31
    Act Density 0.004%

    No Known Activations