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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Serializer
    -0.07
     Saint
    -0.07
    Mapped
    -0.07
     deği
    -0.07
    原则
    -0.07
     Egyptians
    -0.07
    垍
    -0.07
    _SN
    -0.07
    トラ
    -0.07
    정책
    -0.06
    POSITIVE LOGITS
    ḣ
    0.06
     candidacy
    0.06
     cursos
    0.06
    打ち
    0.06
    者が
    0.06
    })↵
    0.06
    هن
    0.06
     systemctl
    0.06
    مرة
    0.06
     thermal
    0.06
    Act Density 0.020%

    No Known Activations