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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ερμαν
    -0.07
    awaii
    -0.06
     Reward
    -0.06
     airlines
    -0.06
    论文
    -0.06
    kır
    -0.06
     bằng
    -0.06
    anj
    -0.06
    	ON
    -0.06
     bbc
    -0.06
    POSITIVE LOGITS
    -wide
    0.07
    吾
    0.07
    ????
    0.06
    PointerType
    0.06
     castle
    0.06
    废
    0.06
    _Do
    0.06
    exampleModalLabel
    0.06
    ville
    0.06
    .OnClickListener
    0.06
    Act Density 0.032%

    No Known Activations