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

    Neuronpedia

    INDEX
    Explanations

    definitions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㪯
    0.44
    <unused335>
    0.42
     चमक
    0.41
     heng
    0.39
    ইংরে
    0.39
     branchNode
    0.39
    葙
    0.39
    杪
    0.39
     Hỏi
    0.39
    癃
    0.39
    POSITIVE LOGITS
    osin
    0.42
     прият
    0.39
    RA
    0.38
    Peter
    0.37
     Peter
    0.37
     viable
    0.37
    apath
    0.36
     pajama
    0.36
     revealed
    0.36
    Rex
    0.36
    Act Density 0.000%

    No Known Activations