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

    Neuronpedia

    INDEX
    Explanations

    Code/text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stitch
    -0.07
    itor
    -0.07
    cta
    -0.07
     identifier
    -0.06
    غر
    -0.06
     Raid
    -0.06
     wła
    -0.06
    Regular
    -0.06
     strr
    -0.06
    minated
    -0.06
    POSITIVE LOGITS
    ，這
    0.07
     Greek
    0.06
     eligibility
    0.06
    การแข
    0.06
     impover
    0.06
     proxies
    0.06
    (contract
    0.06
    );"
    0.06
    abase
    0.06
    /power
    0.06
    Act Density 0.000%

    No Known Activations