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

    Neuronpedia

    INDEX
    Explanations

    Event

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detox
    -0.07
    .price
    -0.07
    	local
    -0.07
     covers
    -0.07
     proof
    -0.07
    _paint
    -0.07
     Regular
    -0.07
     favoured
    -0.07
     coffee
    -0.06
     Avatar
    -0.06
    POSITIVE LOGITS
    회사
    0.07
     �
    0.07
    arn
    0.06
    ��
    0.06
    caa
    0.06
     vX
    0.06
    най
    0.06
    šak
    0.06
    ในป
    0.06
     нерв
    0.06
    Act Density 0.002%

    No Known Activations