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

    Neuronpedia

    INDEX
    Explanations

    .org URLs and code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    1.59
    ۔
    1.16
    は
    1.14
    는
    1.13
     on
    1.10
     شركة
    1.07
    ك
    1.05
    خ
    1.05
    $.
    1.02
    ع
    0.99
    POSITIVE LOGITS
    ?
    1.18
     encont
    1.15
     MOU
    1.06
    us
    1.02
     gubern
    1.02
     ocur
    1.00
     apoi
    0.98
     Org
    0.98
     organis
    0.96
     destinat
    0.96
    Act Density 0.045%

    No Known Activations