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

    Neuronpedia

    INDEX
    Explanations

    function calls and APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    利益
    0.58
    nextSend
    0.43
    inputValue
    0.40
     kepentingan
    0.39
    தாய
    0.39
    accueil
    0.39
    sbParams
    0.39
    वियस
    0.39
    फ्र
    0.38
    客人
    0.38
    POSITIVE LOGITS
    函数
    1.00
     API
    0.98
     함수
    0.96
     APIs
    0.95
     functions
    0.91
    関数
    0.91
     函数
    0.87
     function
    0.85
     funzione
    0.84
     Functions
    0.83
    Act Density 0.105%

    No Known Activations