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

    Neuronpedia

    INDEX
    Explanations

    Aaron

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gev
    -0.07
    /commons
    -0.06
     roam
    -0.06
     Jan
    -0.06
     examples
    -0.06
    ící
    -0.06
     П
    -0.06
    statuses
    -0.06
     jugg
    -0.06
    Дж
    -0.06
    POSITIVE LOGITS
     Aaron
    0.08
    .Focused
    0.07
    Aaron
    0.07
    _tD
    0.07
    AIM
    0.07
    证
    0.07
    /front
    0.07
    ael
    0.07
     Larson
    0.07
    宣
    0.06
    Act Density 0.001%

    No Known Activations