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

    Neuronpedia

    INDEX
    Explanations

    origin and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Binary
    0.48
     काल्पनिक
    0.48
     Boolean
    0.47
    Probability
    0.47
    Sprites
    0.47
     probabilistic
    0.46
     solvable
    0.46
     هاکي
    0.46
    ртуа
    0.46
     Probability
    0.45
    POSITIVE LOGITS
     terroir
    1.42
     artisanal
    1.30
     artisan
    1.23
     sourcing
    1.09
     harvest
    1.05
     farmers
    1.04
     harvesting
    1.04
     petani
    1.04
    harvest
    1.03
     artisans
    1.02
    Act Density 0.105%

    No Known Activations