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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “For
    -0.07
    ('\\
    -0.06
    цію
    -0.06
    (""))↵
    -0.06
    arus
    -0.06
    anford
    -0.06
    ({});↵
    -0.06
    _sal
    -0.06
    marshall
    -0.06
     DataBase
    -0.06
    POSITIVE LOGITS
     diarr
    0.07
    宣
    0.07
    ....
    0.06
     sche
    0.06
    243
    0.06
    ософ
    0.06
    uplic
    0.06
     підпис
    0.06
     sure
    0.06
     Vintage
    0.06
    Act Density 0.000%

    No Known Activations