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

    Neuronpedia

    INDEX
    Explanations

    filename or concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     durumu
    1.32
     contenders
    1.20
    ;'>
    1.16
     tři
    1.14
     chút
    1.12
     hilfre
    1.10
     ayrı
    1.09
     Viele
    1.08
     possa
    1.08
     contender
    1.08
    POSITIVE LOGITS
    o
    1.26
    akun
    1.17
     IPM
    1.04
    ره
    1.03
    ه
    0.99
     fact
    0.98
    Account
    0.98
    g
    0.95
     Commence
    0.95
    lo
    0.94
    Act Density 0.001%

    No Known Activations