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

    Neuronpedia

    INDEX
    Explanations

    energy conversion or stack diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    💒
    0.49
    感兴趣
    0.44
    鸫
    0.43
    进一步
    0.43
     exploración
    0.43
     خواتین
    0.43
     পরবর্তীতে
    0.42
     ediyorum
    0.42
    简单的
    0.41
     seclusion
    0.41
    POSITIVE LOGITS
    ISER
    0.44
    漱
    0.40
     त्यांनी
    0.39
    pple
    0.39
     tir
    0.38
    3
    0.38
    格
    0.38
     etc
    0.37
     भरकर
    0.37
    ANCED
    0.37
    Act Density 0.002%

    No Known Activations