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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Simmons
    -0.07
    _paper
    -0.07
    严
    -0.07
    дает
    -0.06
     stát
    -0.06
     Stevenson
    -0.06
     Tutorial
    -0.06
     zvlášt
    -0.06
     ours
    -0.06
     Glover
    -0.06
    POSITIVE LOGITS
     oran
    0.06
     advice
    0.06
     responsibility
    0.06
    šní
    0.06
     sup
    0.06
    .rate
    0.06
     bosses
    0.06
     improve
    0.06
    /maps
    0.06
     외
    0.06
    Act Density 0.024%

    No Known Activations