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

    Neuronpedia

    INDEX
    Explanations

    code and portability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("</
    -0.09
     William
    -0.09
     bhaineann
    -0.08
    _wh
    -0.08
    Reject
    -0.08
     Eleanor
    -0.08
    ושא
    -0.08
    ्रिय
    -0.08
    जनिक
    -0.08
     Beyoncé
    -0.08
    POSITIVE LOGITS
     portability
    0.11
     адап
    0.11
    跨
    0.10
     adatt
    0.10
     abstraction
    0.10
    兼
    0.10
     adaptable
    0.10
     adaptability
    0.09
     adaptación
    0.09
     interoperability
    0.09
    Act Density 0.019%

    No Known Activations