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

    Neuronpedia

    INDEX
    Explanations

    Juicero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     additional
    0.86
     اندراج
    0.77
    予め
    0.75
     acrylic
    0.74
     accordingly
    0.71
     Additional
    0.70
     adaptability
    0.69
     اضافی
    0.69
    Additional
    0.68
     diagrams
    0.65
    POSITIVE LOGITS
     людей
    1.02
     ludzi
    1.00
     ľud
    1.00
     lidí
    0.97
     ludzie
    0.97
     ljudi
    0.92
     aveva
    0.89
     ľudí
    0.89
    আমার
    0.88
     famosos
    0.88
    Act Density 0.118%

    No Known Activations