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

    Neuronpedia

    INDEX
    Explanations

    merit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vět
    -0.06
     Howe
    -0.06
     kone
    -0.06
    aincontri
    -0.06
     využí
    -0.06
     vulnerable
    -0.06
    	block
    -0.06
    Fax
    -0.06
    $string
    -0.06
    Binder
    -0.06
    POSITIVE LOGITS
     merits
    0.11
     merit
    0.10
    Merit
    0.09
    (stderr
    0.07
     Received
    0.07
    -done
    0.07
    vidia
    0.07
     Articles
    0.07
     residuals
    0.06
    Score
    0.06
    Act Density 0.002%

    No Known Activations