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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Copyright
    -0.07
    очных
    -0.07
    ドラ
    -0.06
     Publishers
    -0.06
    _dice
    -0.06
    .API
    -0.06
     Commerce
    -0.06
    ÄŸ
    -0.06
     Cosmetic
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    almart
    0.06
    _]
    0.06
    물을
    0.06
    .Element
    0.06
    .El
    0.06
    .Lines
    0.06
    阴
    0.06
     tighten
    0.06
     rpm
    0.06
    _experiment
    0.06
    Act Density 0.019%

    No Known Activations