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

    Neuronpedia

    INDEX
    Explanations

    words starting and ending with letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivariate
    0.43
    菂
    0.41
     Thereafter
    0.39
    Koordin
    0.38
    稹
    0.37
    loir
    0.37
    汞
    0.36
     Entered
    0.35
     distanza
    0.35
    Hoa
    0.35
    POSITIVE LOGITS
    したい
    0.39
     spi
    0.37
     会
    0.37
    ↵↵
    0.37
     cool
    0.37
    ピ
    0.37
     ninja
    0.36
     spect
    0.36
     genomic
    0.36
    rise
    0.35
    Act Density 0.001%

    No Known Activations