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

    Neuronpedia

    INDEX
    Explanations

    knowing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    places
    -0.08
    Comparison
    -0.08
     beginners
    -0.07
    comparison
    -0.07
     Starts
    -0.07
    Looking
    -0.07
    From
    -0.07
     começam
    -0.07
    Started
    -0.07
    begin
    -0.07
    POSITIVE LOGITS
     täysin
    0.11
     täiel
    0.11
     vollständig
    0.11
    完全
    0.10
     સંપૂર્ણ
    0.10
    准确
    0.10
     volledig
    0.10
     పూర్త
    0.10
     pinpoint
    0.10
     vollständ
    0.10
    Act Density 0.015%

    No Known Activations