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

    Neuronpedia

    INDEX
    Explanations

    flags as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     производстве
    1.32
     broadband
    1.26
     precipitate
    1.26
     bounding
    1.23
     preoccupied
    1.18
     Predicting
    1.18
     mba
    1.17
     Broadband
    1.16
     hrane
    1.16
     lysis
    1.15
    POSITIVE LOGITS
     entrou
    1.41
    ्स
    1.40
    jší
    1.39
    baixo
    1.29
    オン
    1.24
    țiunea
    1.24
    ᴱ
    1.19
     uncond
    1.18
    ʤ
    1.17
    poder
    1.17
    Act Density 0.000%

    No Known Activations