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 names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bre
    -0.42
     the
    -0.40
     FetchType
    -0.38
     <
    -0.37
     Che
    -0.37
    才有
    -0.37
     Bek
    -0.36
     šo
    -0.36
     caminh
    -0.36
    selectBy
    -0.36
    POSITIVE LOGITS
     Island
    1.55
     island
    1.51
    Island
    1.45
     ISLAND
    1.43
    island
    1.30
     Islands
    1.20
     islands
    1.16
    Islands
    1.09
     Islanders
    1.06
     islanders
    1.06
    Act Density 0.006%

    No Known Activations