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

    Neuronpedia

    INDEX
    Explanations

    pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pattern
    -1.93
     patterns
    -1.80
     Pattern
    -1.61
    pattern
    -1.56
     PATTERN
    -1.49
     Patterns
    -1.48
    Pattern
    -1.45
     patrones
    -1.41
    patterns
    -1.34
     patrón
    -1.31
    POSITIVE LOGITS
    sprecher
    0.57
     nonatomic
    0.50
     bristles
    0.50
     distanciation
    0.49
     activation
    0.48
    activating
    0.46
    ༘
    0.46
     تضيفلها
    0.45
    Defin
    0.44
    activated
    0.44
    Act Density 0.109%

    No Known Activations