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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and their properties

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

    mathematical function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     basah
    -0.41
     tiny
    -0.40
    tiny
    -0.39
     stehenden
    -0.39
    desta
    -0.39
     Mejía
    -0.39
     Putih
    -0.38
     Stad
    -0.38
     oír
    -0.38
    >>>>>>>
    -0.38
    POSITIVE LOGITS
     function
    1.03
     Function
    0.98
    function
    0.94
     Functions
    0.90
     functions
    0.88
    Function
    0.85
    函数
    0.82
     函数
    0.82
     funcion
    0.81
     함수
    0.79
    Act Density 0.085%

    No Known Activations