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

    Neuronpedia

    INDEX
    Explanations

    sustainability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urt
    -0.29
    olog
    -0.26
    Fetching
    -0.26
    $$$$
    -0.25
    éĢ»è¾ij
    -0.24
     cher
    -0.24
    人æµģ
    -0.24
    \Migrations
    -0.24
     malignant
    -0.24
     fetched
    -0.24
    POSITIVE LOGITS
    nung
    0.29
    fall
    0.28
    [ii
    0.26
    éĽ¢
    0.26
    ä¹Ŀ大
    0.25
    ende
    0.25
    ãģ§ãģĹãĤĩãģĨãģĭ
    0.25
    ese
    0.24
    .Commands
    0.24
    寬
    0.24
    Act Density 0.037%

    No Known Activations