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

    Neuronpedia

    INDEX
    Explanations

    (n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('.');↵
    -0.07
     CJ
    -0.06
     Runs
    -0.06
    роничес
    -0.06
     Saved
    -0.06
    ائيل
    -0.06
    лении
    -0.06
     vapor
    -0.06
     =>
↵
    -0.06
     carry
    -0.06
    POSITIVE LOGITS
     donated
    0.07
    造
    0.06
     paramet
    0.06
    簡
    0.06
    304
    0.06
     profitable
    0.06
    _pipe
    0.06
    тер
    0.06
     postupně
    0.06
     ratified
    0.06
    Act Density 0.000%

    No Known Activations