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

    Neuronpedia

    INDEX
    Explanations

    punctuation/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gors
    -0.06
    	command
    -0.06
     highlight
    -0.06
    几个
    -0.06
    ис
    -0.06
    _content
    -0.06
    ofil
    -0.06
     Belarus
    -0.06
    lauf
    -0.06
    検
    -0.06
    POSITIVE LOGITS
     número
    0.07
    .performance
    0.07
     ба
    0.07
     hoş
    0.06
    (NO
    0.06
    iể
    0.06
     🙂
    0.06
     hil
    0.06
    NewLabel
    0.06
     تواند
    0.06
    Act Density 0.008%

    No Known Activations