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

    Neuronpedia

    INDEX
    Explanations

    important points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paci
    2.40
    Organisation
    2.35
     الاجتماعية
    2.26
    binoculars
    2.25
     Brou
    2.24
    ient
    2.24
     Букови
    2.23
     preservative
    2.23
     зару
    2.22
    =$\
    2.17
    POSITIVE LOGITS
    7
    1.37
    rinsic
    1.25
    8
    1.20
    上げ
    1.19
    6
    1.11
    5
    0.99
    4
    0.97
    *>(
    0.96
    々の
    0.95
    9
    0.94
    Act Density 0.042%

    No Known Activations