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

    Neuronpedia

    INDEX
    Explanations

    encouragement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    від
    -0.06
     argue
    -0.06
    _post
    -0.06
     Angela
    -0.06
    /all
    -0.06
     pauses
    -0.06
     ca
    -0.06
     without
    -0.06
     divid
    -0.06
     대
    -0.06
    POSITIVE LOGITS
     work
    0.07
     Μά
    0.07
     tiêu
    0.07
     conna
    0.07
    	↵	↵	↵
    0.06
     činnost
    0.06
     wrestler
    0.06
    ACTION
    0.06
    Rich
    0.06
    _enc
    0.06
    Act Density 0.007%

    No Known Activations