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

    Neuronpedia

    INDEX
    Explanations

    Code and website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umberland
    -0.07
     evolving
    -0.07
     credit
    -0.06
    DataSetChanged
    -0.06
    meldung
    -0.06
     wreck
    -0.06
     Randy
    -0.06
     aDecoder
    -0.06
     Перв
    -0.06
    خف
    -0.06
    POSITIVE LOGITS
    ＼＼
    0.07
     eks
    0.06
    	flag
    0.06
    onu
    0.06
    transactions
    0.06
     tolik
    0.06
    apons
    0.06
    _FULL
    0.06
    	sb
    0.06
     hsv
    0.06
    Act Density 0.000%

    No Known Activations