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

    Neuronpedia

    INDEX
    Explanations

    geographical directions and locations relative to other places

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

    directions and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.54
     scolaire
    -0.54
     législ
    -0.52
     informée
    -0.50
     Inscrivez
    -0.50
     numberOfRows
    -0.47
     fût
    -0.47
     lenker
    -0.46
     thinner
    -0.46
     Infór
    -0.46
    POSITIVE LOGITS
    TopLeft
    0.55
     southwest
    0.51
    bottomRight
    0.48
    topLeft
    0.47
     northeast
    0.47
     Wul
    0.46
     northwest
    0.45
    hysema
    0.44
    ConstraintMaker
    0.43
     Southwest
    0.43
    Act Density 0.008%

    No Known Activations