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

    Neuronpedia

    INDEX
    Explanations

    references to lakes

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

    lake locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Billings
    -0.45
     Prius
    -0.45
    CodeAttribute
    -0.44
    diss
    -0.43
    lioz
    -0.42
     webdriver
    -0.42
     IFF
    -0.41
    chesse
    -0.41
     butter
    -0.40
     enf
    -0.40
    POSITIVE LOGITS
     Lake
    2.25
    Lake
    2.08
     LAKE
    2.02
     lake
    1.68
    lake
    1.63
    LAKE
    1.51
     Lakes
    1.23
     lakes
    1.11
    湖
    1.09
     озера
    1.00
    Act Density 0.003%

    No Known Activations