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

    Neuronpedia

    INDEX
    Explanations

    functions and integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    催
    0.21
     биологи
    0.21
    Hoff
    0.21
    रोना
    0.21
    万人
    0.21
    DNA
    0.20
    ΟΣ
    0.20
     여름
    0.20
     вважа
    0.20
     людей
    0.20
    POSITIVE LOGITS
     métodos
    0.31
    函数
    0.31
     metod
    0.31
    関数
    0.31
     funzione
    0.31
     using
    0.30
     methods
    0.30
     function
    0.30
     functions
    0.30
     함수
    0.30
    Act Density 2.021%

    No Known Activations