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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -con
    -0.07
    	args
    -0.06
     آل
    -0.06
    _ARGS
    -0.06
    شي
    -0.06
     чин
    -0.06
    _turn
    -0.06
    生成
    -0.06
    Most
    -0.06
    ILON
    -0.06
    POSITIVE LOGITS
     reminded
    0.07
     开始
    0.07
     notamment
    0.07
    алася
    0.06
     Nich
    0.06
     Maduro
    0.06
     beneficiaries
    0.06
     overflow
    0.06
    」↵
    0.06
     acknowledged
    0.06
    Act Density 0.079%

    No Known Activations