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

    Neuronpedia

    INDEX
    Explanations

    lists, punctuation, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佢
    2.61
    ungannya
    2.44
     historians
    2.42
    dated
    2.40
     Vee
    2.39
     calendário
    2.34
     itinerary
    2.32
     Barcl
    2.28
     ihn
    2.28
    فير
    2.28
    POSITIVE LOGITS
    rinsic
    3.59
    7
    3.45
    8
    3.11
     instinctively
    3.10
    6
    3.03
    4
    2.92
     combust
    2.90
    5
    2.90
     sublim
    2.88
    3
    2.85
    Act Density 0.317%

    No Known Activations