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

    Neuronpedia

    INDEX
    Explanations

    polynomial operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.56
    在
    0.54
    I
    0.51
    cosmos
    0.49
    Carl
    0.47
    ILL
    0.47
    gn
    0.45
    garden
    0.44
    gl
    0.44
    glazed
    0.44
    POSITIVE LOGITS
     يد
    0.49
     Polynomial
    0.47
     navigateur
    0.44
    กิน
    0.44
     څنګه
    0.43
     فونیټ
    0.43
     জায়গা
    0.42
    ালে
    0.42
    െങ്കിലും
    0.42
    กฎ
    0.41
    Act Density 0.003%

    No Known Activations