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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     statistics
    -0.08
    国家安全
    -0.07
    _upper
    -0.07
     Weiss
    -0.07
     real
    -0.07
    ⊰
    -0.07
    .square
    -0.07
     образования
    -0.07
    提出的
    -0.07
     peripheral
    -0.07
    POSITIVE LOGITS
    PIN
    0.08
    ママ
    0.07
    meter
    0.07
    즙
    0.07
    孺
    0.06
     מש
    0.06
    押し
    0.06
    ゛
    0.06
     ingr
    0.06
    Ẽ
    0.06
    Act Density 0.002%

    No Known Activations