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

    Neuronpedia

    INDEX
    Explanations

    made of, analyzer :, a8, 7al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    尊
    1.46
     身
    1.30
     최소
    1.29
    𝓻
    1.28
    বৃদ্ধ
    1.24
    𝐫
    1.22
     |_{
    1.21
     PM
    1.20
    𝐳
    1.19
     тела
    1.16
    POSITIVE LOGITS
    ishly
    1.46
    Carol
    1.36
    '!
    1.28
     quite
    1.22
     craze
    1.22
     flavor
    1.21
    aloo
    1.19
     ;-)
    1.17
    anything
    1.17
     sorry
    1.16
    Act Density 0.190%

    No Known Activations