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

    Neuronpedia

    INDEX
    Explanations

    from to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zealand
    -0.07
    _NE
    -0.07
    _capabilities
    -0.07
    年轻
    -0.07
    .Nil
    -0.07
     KE
    -0.06
    南海网
    -0.06
    나
    -0.06
    rega
    -0.06
    pagina
    -0.06
    POSITIVE LOGITS
    这场
    0.06
     "")↵↵
    0.06
    ḍ
    0.06
    ORDER
    0.06
     Söz
    0.06
    ��
    0.06
    portunity
    0.06
     encounters
    0.06
    馞
    0.06
    ऋ
    0.06
    Act Density 0.031%

    No Known Activations