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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ابعة
    -0.07
     eds
    -0.07
    Price
    -0.07
     keyboard
    -0.07
     touch
    -0.07
     hearing
    -0.07
     ],
    -0.07
     Ducks
    -0.06
    〉
    -0.06
     died
    -0.06
    POSITIVE LOGITS
     Stealth
    0.06
     domácí
    0.06
    .glob
    0.06
    SSIP
    0.06
    _PED
    0.06
     لازم
    0.06
    SFML
    0.06
     машин
    0.06
    	TEST
    0.05
     мест
    0.05
    Act Density 0.004%

    No Known Activations