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

    Neuronpedia

    INDEX
    Explanations

    definitions of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оплаты
    0.45
     গার্ম
    0.45
     disgusting
    0.44
    شتی
    0.42
    زاده
    0.42
     condado
    0.42
     môžu
    0.42
     prejudices
    0.42
     budou
    0.42
    нтэр
    0.42
    POSITIVE LOGITS
    ){
    0.52
    with
    0.51
    ub
    0.51
    ate
    0.50
    ),
    0.46
    ren
    0.46
    pi
    0.46
    structed
    0.45
     सतत
    0.45
    )?
    0.45
    Act Density 0.007%

    No Known Activations