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

    Neuronpedia

    INDEX
    Explanations

    content produced per day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅಲ್ಲಿ
    0.21
    排行
    0.20
     liturgical
    0.19
     crucifixion
    0.19
     agitation
    0.19
     драма
    0.19
     epistle
    0.18
     courtship
    0.18
    იდან
    0.18
     ganglia
    0.18
    POSITIVE LOGITS
    曰
    0.19
        
    0.18
         
    0.18
    weit
    0.18
    日
    0.17
    akes
    0.17
     عائد
    0.17
    upp
    0.17
     "
    0.17
    would
    0.17
    Act Density 0.001%

    No Known Activations