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

    Neuronpedia

    INDEX
    Explanations

    list items after directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.23
    o
    0.20
     the
    0.19
    летний
    0.18
     thematic
    0.17
     terribly
    0.17
    ثل
    0.16
     definite
    0.16
     kudos
    0.16
     interdiscipl
    0.16
    POSITIVE LOGITS
     equaling
    0.22
     Nhưng
    0.21
     (--
    0.20
     නිසා
    0.20
    だが
    0.20
     -(
    0.19
     কিংবা
    0.19
    但是我
    0.19
     或者
    0.19
     nhưng
    0.19
    Act Density 0.141%

    No Known Activations