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

    Neuronpedia

    INDEX
    Explanations

    defining parameters and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     những
    0.20
     elucid
    0.17
     অন্যতম
    0.17
     attributing
    0.17
    a
    0.16
    the
    0.16
     episcopal
    0.16
    các
    0.16
    sthe
    0.15
     Simón
    0.15
    POSITIVE LOGITS
     system
    0.15
     party
    0.14
     tiver
    0.14
     sampe
    0.14
     multitude
    0.14
     mutta
    0.14
     machine
    0.14
     bolesti
    0.14
    ；
    0.14
     で
    0.13
    Act Density 0.842%

    No Known Activations