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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .React
    -0.07
     roy
    -0.07
     indent
    -0.07
    .Ordinal
    -0.07
     resembles
    -0.07
     month
    -0.07
     vow
    -0.07
    -def
    -0.07
     sod
    -0.07
    .Def
    -0.07
    POSITIVE LOGITS
     Vortrag
    0.12
     keynote
    0.11
     അവതരിപ്പ
    0.09
    会上
    0.09
     وړاندې
    0.09
     Slides
    0.09
     vermittelt
    0.09
     ارائه
    0.09
     charla
    0.08
     talleres
    0.08
    Act Density 0.098%

    No Known Activations