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

    Neuronpedia

    INDEX
    Explanations

    lists and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이미지
    0.38
    ৬০
    0.32
    xcodep
    0.31
    кат
    0.31
     بالأ
    0.31
     সিনেমা
    0.30
    OpportunitiesBy
    0.30
    ৫০
    0.30
    忡
    0.29
    语言
    0.29
    POSITIVE LOGITS
     Stewart
    0.28
     the
    0.28
     Lewis
    0.27
     E
    0.27
     The
    0.27
     Patrick
    0.26
     G
    0.26
     young
    0.26
     Jesus
    0.26
     Denis
    0.25
    Act Density 0.375%

    No Known Activations