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

    Neuronpedia

    INDEX
    Explanations

    Rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Они
    -0.07
     Hyde
    -0.07
    foobar
    -0.07
     نسب
    -0.06
     همکاری
    -0.06
    .enumer
    -0.06
    -extension
    -0.06
    亜
    -0.06
     πό
    -0.06
     Slots
    -0.06
    POSITIVE LOGITS
    ०
    0.07
    (Game
    0.07
     ultimo
    0.06
    ivamente
    0.06
    570
    0.06
    öt
    0.06
    rin
    0.06
    结果
    0.06
    solve
    0.06
     WD
    0.06
    Act Density 0.003%

    No Known Activations