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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of places

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

    border and county names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.52
    Baylor
    -0.52
    tanleria
    -0.48
     MainAxisSize
    -0.48
    Anhalt
    -0.48
     TextAppearance
    -0.47
    TextSpan
    -0.47
    makeText
    -0.46
     Thess
    -0.46
    hopal
    -0.46
    POSITIVE LOGITS
     border
    0.69
     BORDER
    0.63
     Border
    0.60
    chengladbach
    0.59
    Border
    0.54
     Grenz
    0.54
     Tijuana
    0.53
    border
    0.52
    ritsar
    0.51
     frontera
    0.51
    Act Density 0.105%

    No Known Activations