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

    Neuronpedia

    INDEX
    Explanations

    Words indicating the following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    具
    -0.07
     IDF
    -0.07
    /comment
    -0.07
    parcel
    -0.07
    Ả
    -0.06
     příst
    -0.06
    _maker
    -0.06
    faith
    -0.06
     �
    -0.06
    Bi
    -0.06
    POSITIVE LOGITS
    .AddInParameter
    0.07
     pars
    0.07
    ierre
    0.06
     sorts
    0.06
    ={[↵
    0.06
    探
    0.06
     SUPER
    0.06
     Manual
    0.06
     really
    0.06
     Beautiful
    0.06
    Act Density 0.014%

    No Known Activations