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

    Neuronpedia

    INDEX
    Explanations

    important disclaimers and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Haha
    0.59
    Peso
    0.59
    Heute
    0.58
     आल्सो
    0.58
    mensaje
    0.58
    Пу
    0.58
    Якщо
    0.57
    Deze
    0.57
    Maybe
    0.57
    Además
    0.56
    POSITIVE LOGITS
     pro
    0.62
     ro
    0.59
     trans
    0.58
     про
    0.58
     d
    0.58
     re
    0.57
     D
    0.57
     res
    0.57
     un
    0.56
     av
    0.55
    Act Density 0.021%

    No Known Activations