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

    Neuronpedia

    INDEX
    Explanations

    ā

    np_max-act · gemini-2.0-flash

    village names, particularly those that are Romanized or have specific phonetic patterns.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Imagine
    -0.07
     Celebration
    -0.07
     negotiating
    -0.07
    การจ
    -0.07
     making
    -0.06
     scept
    -0.06
    Bachelor
    -0.06
    afc
    -0.06
    MAKE
    -0.06
     Chunk
    -0.06
    POSITIVE LOGITS
    身上
    0.07
    otoxic
    0.06
     مطال
    0.06
    '][
    0.06
    血
    0.06
    異
    0.06
    长
    0.06
    pai
    0.06
    ây
    0.06
    ā
    0.06
    Act Density 0.008%

    No Known Activations