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

    Neuronpedia

    INDEX
    Explanations

    main function declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    survey
    0.39
     Vázquez
    0.38
    袮
    0.38
    icom
    0.37
    দুর
    0.37
    抂
    0.36
    metric
    0.36
    Sí
    0.35
    iav
    0.35
    志森
    0.35
    POSITIVE LOGITS
     arrays
    0.52
     array
    0.48
     funzione
    0.46
     inferred
    0.46
     hàm
    0.43
    函数
    0.43
     функции
    0.42
    창
    0.42
     función
    0.42
    関数
    0.42
    Act Density 0.004%

    No Known Activations