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

    Neuronpedia

    INDEX
    Explanations

    references to seasonal themes and events

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

    Ends a statement with a period

    np_acts-logits-general · gemini-2.0-flash

    general topics and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.90
     disambiguazione
    -0.87
     erſt
    -0.87
     パンチラ
    -0.87
     ſchon
    -0.84
     nahilalakip
    -0.84
     Weiſe
    -0.84
    <unused51>
    -0.84
    <unused8>
    -0.83
    <unused16>
    -0.83
    POSITIVE LOGITS
     because
    0.33
     تق
    0.31
    inc
    0.31
     but
    0.31
     det
    0.30
     pleased
    0.29
    because
    0.28
     porque
    0.27
     hom
    0.25
    when
    0.25
    Act Density 0.351%

    No Known Activations