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

    Neuronpedia

    INDEX
    Explanations

    stance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     med
    -0.06
     зависимости
    -0.06
    混合
    -0.06
    aturdays
    -0.06
    _dialog
    -0.06
     invocation
    -0.06
     override
    -0.06
    supplier
    -0.06
     Mü
    -0.06
     wildcard
    -0.06
    POSITIVE LOGITS
    逆
    0.07
     position
    0.07
     stance
    0.07
     ascend
    0.06
    阶段
    0.06
    ματος
    0.06
    ΕΤ
    0.06
    ंड
    0.06
    EATURE
    0.06
    可能
    0.06
    Act Density 0.011%

    No Known Activations