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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    薄
    -0.06
     glacier
    -0.06
     Barth
    -0.06
     u
    -0.06
     Hük
    -0.06
    oth
    -0.06
    -u
    -0.06
     Donetsk
    -0.06
     glaciers
    -0.06
     Tx
    -0.06
    POSITIVE LOGITS
     suche
    0.07
    PF
    0.07
    abc
    0.07
    (Conv
    0.07
    (zone
    0.06
    では
    0.06
    评论
    0.06
     Submit
    0.06
     chrono
    0.06
    _WIN
    0.06
    Act Density 0.004%

    No Known Activations