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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("//
    -0.06
     Woj
    -0.06
     detective
    -0.06
    ۲۲
    -0.06
     avenue
    -0.06
     André
    -0.06
     winner
    -0.06
    Je
    -0.06
     úřad
    -0.06
     [[[
    -0.06
    POSITIVE LOGITS
     Rational
    0.07
     spills
    0.06
     Cyprus
    0.06
    uckle
    0.06
    ากล
    0.06
    وسط
    0.06
     springs
    0.06
     trips
    0.06
     lith
    0.06
    renc
    0.06
    Act Density 0.002%

    No Known Activations