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
    勿
    -0.07
    伤心
    -0.07
    .getX
    -0.06
    /footer
    -0.06
    惜
    -0.06
    .what
    -0.06
     cudd
    -0.06
    UME
    -0.06
    .START
    -0.06
    <GameObject
    -0.06
    POSITIVE LOGITS
     sentiment
    0.08
     Dan
    0.07
    Enumerable
    0.07
    	trans
    0.07
    海外市场
    0.07
     vi
    0.07
     Iraqi
    0.07
     Dani
    0.07
    _commands
    0.06
    _linear
    0.06
    Act Density 0.034%

    No Known Activations