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

    Neuronpedia

    INDEX
    Explanations

    mentions of lakes

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

    geographical lakes names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Philly
    -0.50
     Philly
    -0.48
     antis
    -0.46
    Bris
    -0.46
     Fod
    -0.45
    ombes
    -0.44
     Bris
    -0.44
     Andersson
    -0.43
     Mandy
    -0.43
    жидан
    -0.43
    POSITIVE LOGITS
     Lake
    1.27
    Lake
    1.20
     lake
    1.18
     LAKE
    1.18
     lakes
    1.06
     Lakes
    1.01
    lake
    0.97
    Lakes
    0.96
    LAKE
    0.86
    lakes
    0.82
    Act Density 0.020%

    No Known Activations