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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ve
    -0.07
     лей
    -0.07
    NSError
    -0.06
     genetically
    -0.06
     Ner
    -0.06
    ‌انبار
    -0.06
     pi
    -0.06
    acial
    -0.06
     Repo
    -0.06
     Uran
    -0.06
    POSITIVE LOGITS
    _Length
    0.08
     PROVID
    0.07
    ologne
    0.06
    .Field
    0.06
    THREAD
    0.06
    _FREQ
    0.06
    .Sub
    0.06
     ativ
    0.06
    (SELECT
    0.06
    .DeepEqual
    0.06
    Act Density 0.003%

    No Known Activations