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

    Neuronpedia

    INDEX
    Explanations

    explicit photos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    为什么
    -0.07
    rozen
    -0.06
    .degree
    -0.06
     Friends
    -0.06
     米
    -0.06
     Policy
    -0.06
     LE
    -0.06
     CHUNK
    -0.06
     ко
    -0.06
     high
    -0.06
    POSITIVE LOGITS
    ilih
    0.06
    arith
    0.06
    \"",↵
    0.06
     vend
    0.06
    urchase
    0.06
    habit
    0.06
        
    0.06
    heed
    0.06
    탄
    0.06
    ansa
    0.06
    Act Density 0.031%

    No Known Activations