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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    を利用して
    -0.08
     Indones
    -0.08
    Consulta
    -0.07
    申請
    -0.07
    args
    -0.07
     engineering
    -0.07
     מנ
    -0.07
    让人
    -0.07
     Zoe
    -0.07
    _geo
    -0.06
    POSITIVE LOGITS
    _stub
    0.07
    cout
    0.07
    -stream
    0.07
    廪
    0.07
    pletion
    0.06
    _Play
    0.06
    utomation
    0.06
    苌
    0.06
     MaterialApp
    0.06
    _tail
    0.06
    Act Density 0.003%

    No Known Activations