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

    Neuronpedia

    INDEX
    Explanations

    instructions and numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebenarnya
    0.52
    다
    0.51
    hiddenMap
    0.50
    யா
    0.49
    ungkinan
    0.48
     membeli
    0.44
    та
    0.43
    ってしまう
    0.43
    uradaki
    0.43
     কিন্তু
    0.43
    POSITIVE LOGITS
     in
    0.72
     $\
    0.54
     as
    0.44
    \
    0.44
     a
    0.43
     e
    0.43
     are
    0.43
     formative
    0.42
     \
    0.42
     Education
    0.42
    Act Density 0.010%

    No Known Activations