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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the preposition "of"

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

    seasons and months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.64
     pinulongan
    -0.63
     nonUne
    -0.58
     disambiguazione
    -0.58
    adaptiveStyles
    -0.56
     defaultstate
    -0.50
    UserScript
    -0.49
     ProtoMessage
    -0.49
     tartalomajánló
    -0.47
     Autorizaciones
    -0.46
    POSITIVE LOGITS
     vuonna
    0.63
     late
    0.58
     בשנת
    0.57
     July
    0.57
    kuuta
    0.54
     سنة
    0.52
     October
    0.50
     June
    0.49
     عام
    0.49
     August
    0.49
    Act Density 0.011%

    No Known Activations