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

    Neuronpedia

    INDEX
    Explanations

    programming operations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    皱
    0.59
     koch
    0.57
     हाथों
    0.55
     hemen
    0.53
     ਇੱਕ
    0.52
     skyrocketing
    0.52
     spandex
    0.52
     kz
    0.52
     canceled
    0.50
    כים
    0.50
    POSITIVE LOGITS
    relevant
    0.66
    ർത്ത
    0.65
     modernisation
    0.63
     NHS
    0.62
     randomised
    0.62
     visualisation
    0.61
     RT
    0.61
     organisations
    0.61
    organisation
    0.61
     organisation
    0.60
    Act Density 0.001%

    No Known Activations