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

    Neuronpedia

    INDEX
    Explanations

    defining what something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    魔法
    0.51
    Cooking
    0.47
    觀
    0.44
    పా
    0.44
    請問
    0.42
     Cooking
    0.42
    槸
    0.40
    硃
    0.40
     způ
    0.40
     Tariff
    0.40
    POSITIVE LOGITS
     isotropic
    0.50
     постра
    0.49
     Emirates
    0.46
     KPSS
    0.46
     fondo
    0.45
    vtk
    0.45
     servicemen
    0.44
     Министерства
    0.44
     anisotropic
    0.43
     militares
    0.43
    Act Density 0.004%

    No Known Activations