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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ляются
    -0.08
    FY
    -0.08
     Serif
    -0.07
    طار
    -0.07
    Go
    -0.07
     максим
    -0.07
     austerity
    -0.06
    ector
    -0.06
    richTextPanel
    -0.06
    rel
    -0.06
    POSITIVE LOGITS
     два
    0.07
    _ID
    0.07
     warmed
    0.07
    _IRQ
    0.06
     sayıda
    0.06
     svůj
    0.06
     another
    0.06
     fuels
    0.06
    目的
    0.06
    、何
    0.06
    Act Density 0.005%

    No Known Activations