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

    Neuronpedia

    INDEX
    Explanations

    memory allocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бампер
    -1.57
     przód
    -1.30
    ഃ
    -1.26
     APPELL
    -1.22
     komplet
    -1.21
    お疲れ
    -1.21
     задний
    -1.20
    thiet
    -1.20
     esportes
    -1.19
     étages
    -1.17
    POSITIVE LOGITS
     if
    1.34
     for
    1.22
     can
    1.17
    研究生
    1.08
    开学
    1.05
     Ukuran
    1.04
    皈
    1.02
    有何
    1.02
    utilisons
    1.01
    裏面
    1.01
    Act Density 0.010%

    No Known Activations