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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辒
    -0.07
    雖
    -0.07
    ⵙ
    -0.07
    ics
    -0.06
     אירועים
    -0.06
    atomy
    -0.06
    ']>;↵
    -0.06
    中国古代
    -0.06
    辌
    -0.06
    _VOID
    -0.06
    POSITIVE LOGITS
    的钱
    0.07
    	renderer
    0.07
    Meter
    0.07
    쿤
    0.07
    .Book
    0.07
     Girl
    0.07
    .pass
    0.07
    .Client
    0.07
     producer
    0.07
    -coded
    0.07
    Act Density 0.002%

    No Known Activations