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

    Neuronpedia

    INDEX
    Explanations

    order of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ok
    1.46
    é
    1.43
    ва
    1.40
    og
    1.29
     asterisk
    1.28
     ravine
    1.25
    龴
    1.23
    ert
    1.20
    ق
    1.19
    िट
    1.18
    POSITIVE LOGITS
    tól
    1.62
    تون
    1.54
    ت
    1.51
    tarif
    1.48
    tedir
    1.45
    czne
    1.41
    تك
    1.39
    నూ
    1.37
    ј
    1.36
     וא
    1.35
    Act Density 0.002%

    No Known Activations