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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рати
    -0.06
     Independ
    -0.06
    егод
    -0.06
     Toll
    -0.06
     tourist
    -0.06
     групи
    -0.06
    esidir
    -0.06
    _expiry
    -0.06
    證
    -0.06
    ivatel
    -0.05
    POSITIVE LOGITS
    :before
    0.11
    ывая
    0.07
    _FOUND
    0.07
     таком
    0.07
     appended
    0.06
    .getElements
    0.06
    Sending
    0.06
     Deferred
    0.06
     indexed
    0.06
     sends
    0.06
    Act Density 0.001%

    No Known Activations