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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and borders

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

    "border", "frontier", or "Mex" followed by punctuation/separators

    np_acts-logits-general · gemini-2.0-flash

    border and frontier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ffilm
    -0.38
    XtraGrid
    -0.38
     Trauer
    -0.37
    lehre
    -0.37
    IContainer
    -0.35
     Armas
    -0.33
    Bretagne
    -0.33
     estés
    -0.33
    Trayectoria
    -0.33
    örungen
    -0.33
    POSITIVE LOGITS
     border
    0.85
     Border
    0.72
     bordering
    0.70
     BORDER
    0.70
     borders
    0.67
    BORDER
    0.61
    border
    0.60
    Border
    0.59
     crossings
    0.59
     frontière
    0.57
    Act Density 0.409%

    No Known Activations