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

    Neuronpedia

    INDEX
    Explanations

    sum of interior angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oper
    0.43
     C
    0.42
     Operation
    0.41
     directly
    0.40
     opl
    0.39
     oper
    0.39
     Wax
    0.38
    OMET
    0.38
     But
    0.38
     measured
    0.38
    POSITIVE LOGITS
    interior
    0.53
    Interior
    0.49
     intérieur
    0.48
     сумма
    0.47
     interior
    0.46
     Interior
    0.46
    ángulos
    0.46
     intérieure
    0.45
    петров
    0.45
    sum
    0.45
    Act Density 0.007%

    No Known Activations