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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mean
    -0.25
    erging
    -0.25
     ink
    -0.25
     Alloy
    -0.24
    visit
    -0.24
    å·¡è§Ĩ
    -0.24
     conflict
    -0.24
    plitude
    -0.24
    =pk
    -0.23
    è¾ĥéĩı
    -0.23
    POSITIVE LOGITS
    .createParallelGroup
    0.28
     bÃło
    0.27
    åįģäºĶæĿ¡
    0.26
    带æĿ¥çļĦ
    0.26
    åĬ±
    0.26
     below
    0.26
    åIJ«
    0.25
    á»Ħ
    0.25
     ниже
    0.25
    趴
    0.25
    Act Density 1.519%

    No Known Activations