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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Walt
    -0.07
     IMD
    -0.07
    .dds
    -0.06
    PDO
    -0.06
    WebElement
    -0.06
     sour
    -0.06
     EA
    -0.06
     smiling
    -0.06
    irror
    -0.06
     wizards
    -0.06
    POSITIVE LOGITS
    ./(
    0.07
     dissolve
    0.07
     recruits
    0.06
    іблі
    0.06
    *>(&
    0.06
    "){
↵
    0.06
    >\
    0.06
    .RequestBody
    0.06
     accumulated
    0.06
    -ли
    0.06
    Act Density 0.043%

    No Known Activations