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

    Neuronpedia

    INDEX
    Explanations

    variety of topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guys
    -0.07
     초
    -0.06
     aggi
    -0.06
    ають
    -0.06
    ,’
    -0.06
     APP
    -0.06
    クラ
    -0.06
    奶
    -0.06
     Amsterdam
    -0.06
     proposes
    -0.06
    POSITIVE LOGITS
     Deus
    0.07
    _reviews
    0.06
    parated
    0.06
     artículo
    0.06
    _rewrite
    0.06
    >User
    0.06
     surfing
    0.06
     IDb
    0.06
    FindBy
    0.06
    _estado
    0.06
    Act Density 0.044%

    No Known Activations