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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships within complex datasets

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

    Comes after a period or comma

    np_acts-logits-general · gemini-2.0-flash

    sentence endings, numerical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.80
     Chwiliwch
    -0.63
     Infórmanos
    -0.57
     detailsLots
    -0.56
     autorytatywna
    -0.55
     Administrativna
    -0.55
     otomatig
    -0.53
    hyrchwyd
    -0.52
     AssemblyCulture
    -0.51
    GTCX
    -0.48
    POSITIVE LOGITS
    forChild
    0.52
    GEBURTS
    0.52
    transQ
    0.49
    KURZBESCHREIBUNG
    0.45
     ModelExpression
    0.41
     Audiodateien
    0.38
     Uang
    0.36
     Teufel
    0.35
     actor
    0.35
    omitempty
    0.34
    Act Density 5.838%

    No Known Activations