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

    Neuronpedia

    INDEX
    Explanations

    rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currencies
    -0.07
    -max
    -0.06
    DOM
    -0.06
     exponential
    -0.06
    ρίας
    -0.06
    ibble
    -0.06
    롱
    -0.06
    	exit
    -0.06
    ické
    -0.06
    _PRE
    -0.06
    POSITIVE LOGITS
    取り
    0.08
    524
    0.07
     نمی
    0.07
     unstable
    0.06
     Sports
    0.06
     نزد
    0.06
    (eval
    0.06
     ความ
    0.06
    391
    0.06
    홍
    0.06
    Act Density 0.048%

    No Known Activations