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

    Neuronpedia

    INDEX
    Explanations

    +++

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    头皮
    -0.08
    湿地
    -0.07
    Verb
    -0.07
    Markdown
    -0.07
    nero
    -0.07
     Chili
    -0.07
    brush
    -0.07
    亚马
    -0.06
     tup
    -0.06
     preamble
    -0.06
    POSITIVE LOGITS
     velit
    0.06
    _CLIENT
    0.06
    �
    0.06
     completely
    0.06
    万千瓦
    0.06
     annum
    0.06
    周恩来
    0.06
     hton
    0.06
    0.06
     neo
    0.06
    Act Density 0.001%

    No Known Activations