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

    Neuronpedia

    INDEX
    Explanations

    first questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อื่นๆ
    0.44
     GAMES
    0.41
    Recursive
    0.39
    +
    0.38
    Flash
    0.38
     쉽게
    0.38
     решения
    0.38
    พลัง
    0.38
    ខ្លួន
    0.37
    $+
    0.37
    POSITIVE LOGITS
     first
    0.57
     પ્રથમ
    0.55
    first
    0.54
     primero
    0.52
    ですね
    0.51
     eerste
    0.50
     första
    0.48
     pertama
    0.48
     prvi
    0.47
     firstly
    0.47
    Act Density 0.149%

    No Known Activations