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

    Neuronpedia

    INDEX
    Explanations

    other [type]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     všetky
    0.44
     wszystkich
    0.42
     všech
    0.41
     wszystkie
    0.39
     всіх
    0.39
     Somalia
    0.39
     всех
    0.38
    isek
    0.38
     όλα
    0.37
    坻
    0.37
    POSITIVE LOGITS
     incre
    0.61
     palpable
    0.57
     posX
    0.56
    ፈጥ
    0.56
     UNNEEDED
    0.55
    Stef
    0.54
    但是
    0.54
     chercheurs
    0.53
     palp
    0.53
    tiff
    0.52
    Act Density 0.009%

    No Known Activations