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

    Neuronpedia

    INDEX
    Explanations

    sizeof (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ках
    1.05
    нти
    1.02
    겐
    1.00
    )।
    0.96
    cia
    0.95
     위해서
    0.91
    garia
    0.90
    色列
    0.90
    为止
    0.89
     HOW
    0.88
    POSITIVE LOGITS
    ان
    1.48
    ا
    1.34
    า
    1.26
     والس
    1.25
    ين
    1.22
    Daniels
    1.22
    です
    1.21
    a
    1.20
    od
    1.16
     הספר
    1.15
    Act Density 0.000%

    No Known Activations