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

    Neuronpedia

    INDEX
    Explanations

    ZOTAC, Jumia, SeaBubble, IRP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    は
    1.53
     The
    1.53
     the
    1.51
    The
    1.50
     a
    1.43
     а
    1.42
     А
    1.41
     الم
    1.39
    が
    1.39
    FA
    1.39
    POSITIVE LOGITS
    od
    1.45
    ရှား
    1.26
    listView
    1.24
    édez
    1.23
    Привет
    1.17
    1.13
    "]').
    1.09
     बुरे
    1.08
     पहलू
    1.07
    ListComponent
    1.07
    Act Density 0.727%

    No Known Activations