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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, particularly corners of a defined area or object

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

    corners and sides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.53
    Geplaatst
    -0.50
    parsedMessage
    -0.49
    IntOverflow
    -0.49
     surla
    -0.49
     otomatig
    -0.48
    цездатний
    -0.47
     propOrder
    -0.46
    \{\\
    -0.46
    DBNull
    -0.46
    POSITIVE LOGITS
     corner
    0.80
     esquina
    0.62
    corner
    0.59
     CORNER
    0.52
    ValueStyle
    0.49
    Corner
    0.48
    highest
    0.47
    隅
    0.47
     Ecke
    0.47
     highest
    0.45
    Act Density 0.009%

    No Known Activations