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

    Neuronpedia

    INDEX
    Explanations

    paella

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    1.21
    ور
    1.16
     be
    1.08
     U
    1.05
    ing
    1.02
    us
    1.01
     C
    1.00
     K
    0.99
     B
    0.98
     A
    0.94
    POSITIVE LOGITS
     pokies
    1.20
    dır
    0.93
     ημέ
    0.89
     actúa
    0.86
     gerçekleştir
    0.85
     دیگری
    0.84
    ชนะ
    0.84
     obtenir
    0.84
    ת
    0.84
    企業の
    0.83
    Act Density 0.000%

    No Known Activations