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

    Neuronpedia

    INDEX
    Explanations

    Polynomial.monomial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Happiness
    0.34
    Mâc
    0.34
    畛
    0.34
    婀
    0.33
    𒄩
    0.32
    บริการ
    0.32
    Архі
    0.32
    دە
    0.32
    Jähr
    0.32
     జాగ్ర
    0.32
    POSITIVE LOGITS
     therefore
    0.45
     Thus
    0.44
     Therefore
    0.44
     thus
    0.43
     quindi
    0.42
     ;
    0.42
     resulted
    0.39
     resulting
    0.39
    Thus
    0.38
     nên
    0.38
    Act Density 0.036%

    No Known Activations