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

    Neuronpedia

    INDEX
    Explanations

    measured

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     files
    -0.07
     websites
    -0.07
     fleet
    -0.07
    efficient
    -0.06
    uges
    -0.06
     subsidies
    -0.06
     hatch
    -0.06
    foon
    -0.06
     rifles
    -0.06
     servers
    -0.06
    POSITIVE LOGITS
    _pixels
    0.07
    .DataPropertyName
    0.07
    ']):↵
    0.07
    "',↵
    0.06
    ังกฤษ
    0.06
    .tx
    0.06
    __':↵
    0.06
    "){
↵
    0.06
     także
    0.06
    $criteria
    0.06
    Act Density 0.021%

    No Known Activations