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

    Neuronpedia

    INDEX
    Explanations

    by followed by a verb or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    K
    1.15
    ية
    1.14
    in
    1.02
    ل
    1.00
    ר
    0.98
    ar
    0.91
    en
    0.89
    em
    0.89
    ن
    0.88
    J
    0.85
    POSITIVE LOGITS
    '
    1.30
     and
    0.89
    งาน
    0.89
    는데
    0.87
    จะ
    0.86
     by
    0.85
    지
    0.83
     virtue
    0.82
    cation
    0.82
    0.82
    Act Density 0.176%

    No Known Activations