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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    哚
    -0.07
    .opacity
    -0.06
     Liberals
    -0.06
    �
    -0.06
    <O
    -0.06
    😽
    -0.06
     TJ
    -0.06
    ographers
    -0.06
    🙋
    -0.06
    rowing
    -0.06
    POSITIVE LOGITS
     Basement
    0.07
     Dungeons
    0.07
     asyncio
    0.07
    Cut
    0.07
     która
    0.07
     acest
    0.07
    COMPARE
    0.06
    趕
    0.06
    _decode
    0.06
    地标
    0.06
    Act Density 0.088%

    No Known Activations