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

    Neuronpedia

    INDEX
    Explanations

    cognitive function tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خی
    -0.07
    ил
    -0.07
     एड
    -0.06
    _SIDE
    -0.06
     fragmented
    -0.06
     サ
    -0.06
     Dav
    -0.06
    /full
    -0.06
     RAD
    -0.06
     Gems
    -0.06
    POSITIVE LOGITS
     broccoli
    0.07
    linik
    0.06
     Exactly
    0.06
    =tmp
    0.06
     فيها
    0.06
    وک
    0.06
    .newLine
    0.06
     Blonde
    0.06
    状況
    0.06
    isto
    0.06
    Act Density 0.009%

    No Known Activations