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

    Neuronpedia

    INDEX
    Explanations

    defining concepts and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     канторы
    0.67
     lineColorSpace
    0.66
     እንቅስቃሴ
    0.66
    }}$
    0.65
     коли
    0.65
     изменения
    0.63
     рэгістрацыі
    0.63
     houseplants
    0.63
    ﻜ
    0.62
     योजनाओं
    0.62
    POSITIVE LOGITS
    ad
    1.17
    u
    1.00
    s
    0.89
    i
    0.88
    AN
    0.87
    is
    0.86
    ak
    0.85
    r
    0.83
    c
    0.83
    e
    0.82
    Act Density 0.322%

    No Known Activations