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

    Neuronpedia

    INDEX
    Explanations

    places and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dn
    0.37
    幅度
    0.37
     televis
    0.36
     गाँ
    0.36
    ordelen
    0.36
     \%
    0.35
     obsah
    0.35
    忱
    0.35
     crc
    0.35
    线上
    0.35
    POSITIVE LOGITS
    goers
    0.64
     specializing
    0.64
     specialising
    0.62
     संचालक
    0.60
    कर्मी
    0.59
     staff
    0.59
     halls
    0.56
    staff
    0.56
    ध्यक्ष
    0.55
     frequented
    0.55
    Act Density 0.067%

    No Known Activations