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

    Neuronpedia

    INDEX
    Explanations

    principles and speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    結合
    0.55
    Voice
    0.50
    Dimensions
    0.49
    Balance
    0.48
    Analysis
    0.48
    Host
    0.48
    GitHub
    0.48
    Readme
    0.48
    А
    0.47
    Points
    0.47
    POSITIVE LOGITS
     porridge
    0.55
     tard
    0.53
     manic
    0.52
     glaze
    0.52
    cana
    0.52
     manicure
    0.50
     can
    0.50
     pagi
    0.50
     nourrir
    0.50
     enanti
    0.49
    Act Density 0.001%

    No Known Activations