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

    Neuronpedia

    INDEX
    Explanations

    screen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出口
    -0.06
     송
    -0.06
    	ip
    -0.06
    ید
    -0.06
    _KEEP
    -0.06
     розрах
    -0.06
    Cc
    -0.06
    PEnd
    -0.06
     викон
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     rodents
    0.06
    Modifier
    0.06
     deaf
    0.06
    ��
    0.06
     messageId
    0.06
     Naomi
    0.06
     divisive
    0.06
     dull
    0.06
     olduğundan
    0.06
     retailer
    0.06
    Act Density 0.018%

    No Known Activations