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

    Neuronpedia

    INDEX
    Explanations

    various formats of URLs and web links

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

    category followed by classifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    melidir
    -0.37
     abger
    -0.33
     hacerlo
    -0.33
     Weiter
    -0.31
     libremente
    -0.30
     conformidad
    -0.30
     conformément
    -0.29
    diğini
    -0.29
     confiable
    -0.28
     fácilmente
    -0.27
    POSITIVE LOGITS
    Portail
    1.00
    GEBURTSDATUM
    0.94
    Datuak
    0.91
     autorytatywna
    0.87
    :✨
    0.84
     الحره
    0.84
    Portale
    0.81
    بوابة
    0.80
     propOrder
    0.78
    ----</
    0.74
    Act Density 0.002%

    No Known Activations