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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Geographic directions (East, Northwest, etc.)

    np_acts-logits-general · gemini-2.0-flash

    geographic directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thread
    -0.52
    Log
    -0.46
     للمعارف
    -0.44
     jScrollPane
    -0.42
    </table>
    -0.41
    pran
    -0.41
    globalData
    -0.41
     sfor
    -0.40
    annotation
    -0.40
    illaume
    -0.40
    POSITIVE LOGITS
     corner
    0.93
     CORNER
    0.79
     CWE
    0.78
     Corner
    0.77
     quadrant
    0.76
    Corner
    0.76
    TagHelper
    0.75
    corner
    0.73
     corners
    0.72
    fromnode
    0.68
    Act Density 0.140%

    No Known Activations