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

    Neuronpedia

    INDEX
    Explanations

    describing properties or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IMPORTED
    0.40
    inerary
    0.38
    韬
    0.37
    Í
    0.37
    Hey
    0.37
    避
    0.36
     зо
    0.36
     Fiziki
    0.36
    Export
    0.36
     कहां
    0.35
    POSITIVE LOGITS
     따라
    0.43
     নিয়ম
    0.40
     Anth
    0.39
     XT
    0.39
     peri
    0.39
     SB
    0.38
     पूरा
    0.38
     मेघ
    0.37
     থ
    0.36
     pagal
    0.36
    Act Density 0.004%

    No Known Activations