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

    Neuronpedia

    INDEX
    Explanations

    programming elements related to mathematical functions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical trigonometric functions (sin, cos)

    np_acts-logits-general · gemini-2.0-flash

    cos and sin mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OwnProperty
    -0.54
     Diallo
    -0.45
    fromnode
    -0.45
     Comptroller
    -0.45
    lobal
    -0.43
     miel
    -0.42
    kunt
    -0.42
     amb
    -0.42
     udaler
    -0.41
    รับ
    -0.41
    POSITIVE LOGITS
    cos
    1.37
     cos
    1.31
     cosine
    1.31
     sin
    1.28
    sin
    1.26
    Cos
    1.19
    Sin
    1.18
     Sin
    1.14
     Cos
    1.09
    COS
    1.07
    Act Density 0.389%

    No Known Activations