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

    Neuronpedia

    INDEX
    Explanations

    patterns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Logic
    1.13
     logic
    1.10
     logical
    1.04
     logique
    1.03
     Logical
    1.01
     логи
    1.00
    逻辑
    0.99
     logics
    0.98
    Logic
    0.97
     lógica
    0.93
    POSITIVE LOGITS
    quant
    0.81
     quant
    0.79
    Pattern
    0.78
    Patterns
    0.76
    ScreenBinding
    0.76
    Names
    0.73
    Quant
    0.71
     Pattern
    0.70
     patterns
    0.70
     pattern
    0.70
    Act Density 0.331%

    No Known Activations