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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    頻
    -0.08
    manent
    -0.08
    廆
    -0.07
    坋
    -0.07
    Enh
    -0.07
    ;%
    -0.07
     �
    -0.07
    ypo
    -0.07
     simplest
    -0.07
     ünl
    -0.07
    POSITIVE LOGITS
    fortawesome
    0.07
    clamation
    0.07
    *****↵↵
    0.07
    下跌
    0.07
    rage
    0.07
    _gradient
    0.07
     underline
    0.07
     Giáo
    0.07
    .cart
    0.07
     hãy
    0.07
    Act Density 0.001%

    No Known Activations