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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    john
    -0.07
    los
    -0.07
     viruses
    -0.07
    FromDate
    -0.07
     ای
    -0.06
     filme
    -0.06
    orse
    -0.06
    Total
    -0.06
    itor
    -0.06
     strives
    -0.06
    POSITIVE LOGITS
    @RestController
    0.07
    ccd
    0.07
    ुलन
    0.06
     palate
    0.06
     Со
    0.06
    .BufferedReader
    0.06
    ,,
    0.06
    conut
    0.06
    945
    0.06
    .acc
    0.06
    Act Density 0.053%

    No Known Activations