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

    Neuronpedia

    INDEX
    Explanations

    Lake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tob
    -0.07
     Hubb
    -0.07
     tř
    -0.07
     gv
    -0.06
     Amber
    -0.06
    urar
    -0.06
     Rob
    -0.06
     Popup
    -0.06
     Merlin
    -0.06
    stackpath
    -0.06
    POSITIVE LOGITS
     Lake
    0.15
    Lake
    0.13
     lake
    0.13
     Lakes
    0.09
    ake
    0.09
    lake
    0.08
    akes
    0.08
     lakes
    0.08
    anka
    0.08
     judge
    0.07
    Act Density 0.008%

    No Known Activations