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

    Neuronpedia

    INDEX
    Explanations

    Code/programming errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    реж
    -0.06
     petition
    -0.06
    _pct
    -0.06
     facilities
    -0.06
     Resolution
    -0.06
    \"><
    -0.06
     Especially
    -0.06
     жит
    -0.06
     Facilities
    -0.06
     Bern
    -0.06
    POSITIVE LOGITS
     últimos
    0.08
    (AF
    0.08
    الیا
    0.07
     confuse
    0.06
    840
    0.06
    Api
    0.06
     relieve
    0.06
     menos
    0.06
    альных
    0.06
    -non
    0.06
    Act Density 0.013%

    No Known Activations