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

    Neuronpedia

    INDEX
    Explanations

    funny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (region
    -0.07
    Object
    -0.06
    _NUM
    -0.06
    Архівовано
    -0.06
    ชาว
    -0.06
    OrNil
    -0.06
    尚
    -0.06
    헤
    -0.06
    almost
    -0.06
     :"
    -0.06
    POSITIVE LOGITS
     //@
    0.07
     دلار
    0.07
     ανά
    0.07
    .ColumnName
    0.07
    frei
    0.06
    的一
    0.06
    hardt
    0.06
    _Item
    0.06
    Series
    0.06
    .handle
    0.06
    Act Density 0.005%

    No Known Activations