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

    Neuronpedia

    INDEX
    Explanations

    even framed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aboard
    0.39
    EnableCOMDAT
    0.38
     deceit
    0.38
     Uttarakhand
    0.38
     überall
    0.37
    ্ব
    0.37
    adə
    0.37
     raconte
    0.36
     compradores
    0.36
     pundits
    0.36
    POSITIVE LOGITS
     EVEN
    0.43
    TEC
    0.42
     lower
    0.39
     even
    0.39
    KE
    0.39
     अगदी
    0.38
    Idx
    0.36
     ٹیکسٹ
    0.36
     ミニ
    0.36
    regardless
    0.36
    Act Density 0.060%

    No Known Activations