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

    Neuronpedia

    INDEX
    Explanations

    multiplication and division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rebel
    0.40
     sur
    0.40
     insurg
    0.39
     consistently
    0.39
    sur
    0.38
     sin
    0.38
     jest
    0.37
     Sur
    0.37
     j
    0.37
    <0xB2>
    0.36
    POSITIVE LOGITS
     multiplied
    0.50
     multiplication
    0.47
     multiplying
    0.47
    Multiply
    0.42
     Multiplication
    0.40
     multiplies
    0.40
    院长
    0.40
    鬻
    0.38
    Hundred
    0.38
    setScale
    0.38
    Act Density 0.077%

    No Known Activations