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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vollen
    0.48
    사와
    0.48
     élo
    0.46
    posaż
    0.43
    细菌
    0.43
    চিব
    0.43
    newName
    0.43
     হুই
    0.42
    肌肤
    0.42
    ญาต
    0.42
    POSITIVE LOGITS
     function
    0.63
     nonnegative
    0.49
    函数
    0.48
    функ
    0.47
     operation
    0.47
     min
    0.46
    (),
    0.45
     piecewise
    0.45
    тельств
    0.45
     функ
    0.44
    Act Density 0.017%

    No Known Activations