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

    Neuronpedia

    INDEX
    Explanations

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    -1.51
    ,
    -1.28
    .
    -1.27
    eronau
    -1.22
     to
    -1.20
     said
    -1.14
     according
    -1.12
     aforesaid
    -1.07
    <>
    -1.05
    mnop
    -0.96
    POSITIVE LOGITS
    کفش
    1.41
    آموزش
    1.33
    以及
    1.27
    نحوه
    1.21
     appré
    1.20
    بهترین
    1.19
     prét
    1.17
     trän
    1.16
    αιν
    1.16
    دانلود
    1.16
    Act Density 0.023%

    No Known Activations