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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     casual
    -0.08
     ọ
    -0.07
     HOM
    -0.07
     несов
    -0.07
    Chrom
    -0.07
     चोट
    -0.07
    _spec
    -0.07
     घंट
    -0.07
     división
    -0.07
     circonst
    -0.07
    POSITIVE LOGITS
    成功
    0.15
     exitos
    0.15
     exemplary
    0.15
     Successful
    0.14
    Successful
    0.14
     সফল
    0.14
     successful
    0.14
     ಯಶ
    0.14
     విజయ
    0.14
    successful
    0.14
    Act Density 0.173%

    No Known Activations