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
    -1.34
    pattern
    -1.31
     Pattern
    -1.28
    Pattern
    -1.21
    out
    -0.96
     mechanism
    -0.95
     equal
    -0.94
     PATTERN
    -0.87
    equal
    -0.83
     Mechanism
    -0.83
    POSITIVE LOGITS
    isations
    0.88
    
    0.86
    oneofs
    0.82
     initComponents
    0.80
    +#+#
    0.80
    AndEndTag
    0.79
    ConstraintMaker
    0.79
     للمعارف
    0.79
    isation
    0.78
    Sucesor
    0.71
    Act Density 0.197%

    No Known Activations