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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出来的
    -0.07
    .openqa
    -0.07
    _relations
    -0.07
     mute
    -0.07
     jackets
    -0.07
    螋
    -0.06
    第九
    -0.06
     Gone
    -0.06
     permits
    -0.06
    dera
    -0.06
    POSITIVE LOGITS
    ș
    0.07
    珪
    0.07
    良い
    0.07
    粼
    0.07
    administr
    0.07
    悟
    0.07
    ഷ
    0.07
    ര
    0.07
    dag
    0.07
    spir
    0.07
    Act Density 0.015%

    No Known Activations