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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਰ
    0.44
    wurf
    0.44
    by
    0.43
    at
    0.43
    ও
    0.42
    G
    0.42
     L
    0.41
     wied
    0.41
     tightening
    0.40
     zacz
    0.40
    POSITIVE LOGITS
    镭
    0.52
     توضی
    0.51
     ассорти
    0.50
     đức
    0.49
     müşteri
    0.48
    的市场
    0.48
     dSample
    0.47
     autocor
    0.47
     كوساين
    0.47
     productColor
    0.46
    Act Density 0.000%

    No Known Activations