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

    Neuronpedia

    INDEX
    Explanations

    proper names of people.

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الحره
    -1.04
    tvguidetime
    -0.92
    最快更新
    -0.87
    :✨
    -0.85
     &___
    -0.85
    Portale
    -0.82
     CURIAM
    -0.82
    Personendaten
    -0.82
    发表于
    -0.81
    InputBorder
    -0.81
    POSITIVE LOGITS
    <bos>
    1.41
    ’
    0.63
    '
    0.59
    .
    0.51
    in
    0.50
    ↵
    0.45
    -
    0.45
    my
    0.44
      
    0.44
    ,
    0.44
    Act Density 6.516%

    No Known Activations