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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्श
    -0.08
     Bib
    -0.07
    яч
    -0.07
    /my
    -0.07
    лов
    -0.07
    忆
    -0.06
     El
    -0.06
     Nearly
    -0.06
     discovered
    -0.06
    льт
    -0.06
    POSITIVE LOGITS
    ))/(
    0.07
    EqualityComparer
    0.06
    .azure
    0.06
     spanning
    0.06
     borrowers
    0.06
    }`,
    0.06
    Listening
    0.06
     isChecked
    0.06
    remaining
    0.06
     typings
    0.06
    Act Density 0.023%

    No Known Activations