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

    Neuronpedia

    INDEX
    Explanations

    numerical data regarding geographical coordinates and elevation

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

    start_of_turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.42
    
    -0.41
     internetowa
    -0.40
     cuillère
    -0.40
     toalha
    -0.39
     cadeira
    -0.39
     conveyed
    -0.39
    httphttps
    -0.39
     aislada
    -0.38
     aranha
    -0.38
    POSITIVE LOGITS
     nakalista
    0.62
     auffi
    0.54
    styleType
    0.50
     $_"
    0.49
     dezelve
    0.49
     $_(
    0.45
     '&#
    0.45
    principalTable
    0.43
    Huile
    0.43
    BeginContext
    0.43
    Act Density 0.030%

    No Known Activations