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

    Neuronpedia

    INDEX
    Explanations

    page numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     XV
    0.45
     III
    0.43
     II
    0.42
    XV
    0.40
     XXIV
    0.39
     ৪৯
    0.38
    B
    0.38
    II
    0.38
     £
    0.37
    -$
    0.36
    POSITIVE LOGITS
    嘰
    0.45
     roka
    0.43
     اضاف
    0.41
    ার্টমেন্ট
    0.40
     sinusoidal
    0.39
     interfacial
    0.39
     ई
    0.39
     맛있
    0.39
     PEP
    0.38
    ິງ
    0.38
    Act Density 0.000%

    No Known Activations