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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bu
    -0.07
     annot
    -0.07
    ovable
    -0.07
     aviation
    -0.07
    obile
    -0.07
     Фед
    -0.07
    values
    -0.06
     swap
    -0.06
     Coverage
    -0.06
     V
    -0.06
    POSITIVE LOGITS
    _PIN
    0.07
     तरफ
    0.07
    ربية
    0.07
    ORIGINAL
    0.06
    搭
    0.06
     itemType
    0.06
    	widget
    0.06
     coherent
    0.06
     *,
    0.06
    _ac
    0.06
    Act Density 0.030%

    No Known Activations