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

    Neuronpedia

    INDEX
    Explanations

    knowledge management and transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    1.20
    ki
    1.09
    。
    1.03
    ta
    1.02
     метода
    1.02
    times
    1.01
    vět
    1.01
    cnn
    0.99
    。<
    0.96
    、
    0.95
    POSITIVE LOGITS
    י
    2.05
    ר
    1.80
     knowledge
    1.74
    ي
    1.72
    ות
    1.55
    ;
    1.54
    )
    1.52
    _
    1.41
    า
    1.40
    ה
    1.40
    Act Density 0.067%

    No Known Activations