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

    Neuronpedia

    INDEX
    Explanations

    causes or intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    満足
    1.10
    ঙ্কের
    1.07
     polysaccharide
    1.04
     ше
    1.04
     Comfortable
    1.01
     Curved
    0.98
     lobes
    0.98
     Съ
    0.97
     Certainly
    0.97
     ಮಟ್ಟ
    0.96
    POSITIVE LOGITS
    okhlov
    1.09
    ojn
    1.02
    ار
    0.94
    իկ
    0.92
    nú
    0.91
    ائها
    0.90
    HING
    0.87
     Subsect
    0.87
     Asturias
    0.87
     việc
    0.86
    Act Density 0.001%

    No Known Activations