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 names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ombes
    -0.43
     bæ
    -0.38
     ση
    -0.37
    жидан
    -0.36
     않았
    -0.35
    hubaneswar
    -0.34
     przys
    -0.34
    IMDG
    -0.33
    urator
    -0.33
    importanza
    -0.33
    POSITIVE LOGITS
     Lake
    1.93
    Lake
    1.80
     LAKE
    1.59
    LAKE
    1.23
    lake
    1.15
     Lakes
    1.05
     lake
    1.03
    Lakes
    0.95
     Lago
    0.88
    lakes
    0.79
    Act Density 0.003%

    No Known Activations