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

    Neuronpedia

    INDEX
    Explanations

    asking about context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Interfaz
    0.83
     equipado
    0.80
     }{}_{\
    0.77
    Ethoxy
    0.76
    Genetic
    0.76
    ogén
    0.76
     tradizione
    0.75
    ٰذا
    0.75
    Semester
    0.73
    Protocol
    0.73
    POSITIVE LOGITS
     of
    2.53
    ของการ
    2.16
     của
    2.09
    ของ
    2.08
     ofthe
    1.81
    នៃការ
    1.67
     của
    1.65
     της
    1.65
    នៃ
    1.65
     ของ
    1.60
    Act Density 1.098%

    No Known Activations