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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
    future
    -0.07
    IMG
    -0.07
    shaw
    -0.07
    由於
    -0.07
     YELLOW
    -0.07
    iParam
    -0.07
    _wrapper
    -0.06
     paran
    -0.06
    Parameters
    -0.06
    POSITIVE LOGITS
     Microwave
    0.07
    会上
    0.06
    מייל
    0.06
    .bytes
    0.06
    רוט
    0.06
    <DateTime
    0.06
    >--
    0.06
     bottles
    0.06
     Streets
    0.06
     Replay
    0.06
    Act Density 0.008%

    No Known Activations