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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /device
    -0.07
    _decay
    -0.07
     finds
    -0.07
     }
    -0.07
    isNew
    -0.07
    /run
    -0.07
    so
    -0.06
     speaking
    -0.06
     wasting
    -0.06
    _in
    -0.06
    POSITIVE LOGITS
    اسان
    0.06
     hyster
    0.06
     leicht
    0.06
     мист
    0.06
     Закону
    0.06
    čemž
    0.06
    scar
    0.06
    бер
    0.06
     Май
    0.06
    召
    0.06
    Act Density 0.068%

    No Known Activations