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

    Neuronpedia

    INDEX
    Explanations

    previously seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یسم
    1.13
    irce
    1.07
     også
    1.05
     också
    1.04
    isti
    1.03
     đóng
    0.97
    urpose
    0.94
    áz
    0.94
    بری
    0.92
     orthogonality
    0.92
    POSITIVE LOGITS
    ة
    1.31
     decir
    1.21
     demean
    1.18
    Salle
    1.16
    Tuy
    1.15
    ת
    1.14
     tortoises
    1.12
     Lad
    1.09
    ทย
    1.09
     улицы
    1.07
    Act Density 0.000%

    No Known Activations