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

    Neuronpedia

    INDEX
    Explanations

    Article endings with references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ontent
    -0.07
    iyoruz
    -0.06
    زيز
    -0.06
     toddlers
    -0.06
     Dest
    -0.06
    ):-
    -0.06
    .Our
    -0.06
    >>>>>>>
    -0.06
     base
    -0.06
    izacion
    -0.06
    POSITIVE LOGITS
    ดา
    0.07
     smlou
    0.06
    daş
    0.06
     blogging
    0.06
     meas
    0.06
    aim
    0.06
    ...");↵
    0.06
     Hammond
    0.06
     sns
    0.06
     Books
    0.06
    Act Density 0.027%

    No Known Activations