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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zao
    -0.09
    （土
    -0.08
     Xan
    -0.08
     xmlhttp
    -0.08
    ianza
    -0.08
    （日
    -0.08
     وایي
    -0.08
     Roses
    -0.08
     وايي
    -0.07
    .mc
    -0.07
    POSITIVE LOGITS
     distributions
    0.07
     hunting
    0.07
     пер
    0.07
     распредел
    0.07
     ele
    0.07
     перег
    0.07
     distribution
    0.07
    (log
    0.07
     ):↵
    0.07
     accounting
    0.07
    Act Density 0.085%

    No Known Activations