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

    Neuronpedia

    INDEX
    Explanations

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هُ
    2.39
    €™
    2.28
     ejempl
    2.10
    ه
    2.06
    $.
    2.06
    कर
    2.00
     μεταξύ
    1.96
     deem
    1.95
    гава
    1.95
    ্বর
    1.91
    POSITIVE LOGITS
    ع
    2.23
     tangent
    2.18
    ticks
    2.02
    é
    1.97
     ऑफ
    1.96
     disso
    1.94
    t
    1.93
     Hồ
    1.91
    al
    1.91
    me
    1.89
    Act Density 0.240%

    No Known Activations