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

    Neuronpedia

    INDEX
    Explanations

    references to islands

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

    islands and island locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.51
     onCancelled
    -0.50
    aarrggbb
    -0.50
     initComponents
    -0.49
     Soma
    -0.44
     <<<<<<<<<<<<<<
    -0.43
    tangentMode
    -0.43
    TableBody
    -0.43
    FTFY
    -0.42
    HandlerContext
    -0.42
    POSITIVE LOGITS
     island
    0.52
    tanleria
    0.47
     Island
    0.45
    Island
    0.44
     Insel
    0.42
     islands
    0.42
     ISLAND
    0.41
     ilha
    0.41
     Crusoe
    0.40
    island
    0.39
    Act Density 0.132%

    No Known Activations