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

    Neuronpedia

    INDEX
    Explanations

    Southeast Asia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原因之一
    -0.07
    隐蔽
    -0.06
     amazingly
    -0.06
    	ERR
    -0.06
     Provide
    -0.06
    处处长
    -0.06
    芸
    -0.06
     treasury
    -0.06
    competition
    -0.06
    ካ
    -0.06
    POSITIVE LOGITS
     rows
    0.07
    煽
    0.07
     teen
    0.07
    �
    0.07
     fetching
    0.07
     chụp
    0.07
    ListItemText
    0.07
    /base
    0.06
     fix
    0.06
    �
    0.06
    Act Density 0.070%

    No Known Activations