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

    Neuronpedia

    INDEX
    Explanations

    references to lakes and ponds

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

    named lakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DPD
    -0.55
     Foul
    -0.55
     CFA
    -0.52
     antis
    -0.52
     PMI
    -0.50
     Mandy
    -0.50
    chopped
    -0.49
    Bris
    -0.49
    んご
    -0.48
    samurai
    -0.48
    POSITIVE LOGITS
     lake
    2.03
     Lake
    1.84
    Lake
    1.77
     LAKE
    1.75
     lakes
    1.67
    lake
    1.52
    LAKE
    1.38
     Lakes
    1.30
    Lakes
    1.25
    lakes
    1.19
    Act Density 0.004%

    No Known Activations