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

    Neuronpedia

    INDEX
    Explanations

    Hypothetical questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    бо
    -0.07
    上级
    -0.07
     mình
    -0.07
    (Me
    -0.07
    ToDo
    -0.07
    .");↵↵
    -0.07
    成功
    -0.07
    哄
    -0.07
    レビュー
    -0.06
    تعبير
    -0.06
    POSITIVE LOGITS
    ż
    0.07
    społ
    0.07
     responsiveness
    0.07
    Ḥ
    0.07
    ctest
    0.07
    zw
    0.07
    ザ
    0.06
    极端
    0.06
     olacaktır
    0.06
     Serum
    0.06
    Act Density 0.005%

    No Known Activations