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

    Neuronpedia

    INDEX
    Explanations

    multi-stage process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ded
    0.43
    timetable
    0.42
     timetable
    0.40
    street
    0.39
     condensate
    0.39
     timing
    0.38
     speed
    0.38
    mol
    0.38
     Rye
    0.38
    thirty
    0.38
    POSITIVE LOGITS
     искус
    0.51
    étrica
    0.50
     geração
    0.49
     infraestructura
    0.49
     қили
    0.48
     जितने
    0.48
    ك
    0.46
    ınt
    0.46
    龴
    0.46
     има
    0.46
    Act Density 0.001%

    No Known Activations