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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rests
    -0.07
     prominent
    -0.06
     deps
    -0.06
     їй
    -0.06
     человек
    -0.06
     مشاهده
    -0.06
     свет
    -0.06
    graphs
    -0.06
     mega
    -0.06
    -прав
    -0.06
    POSITIVE LOGITS
    irie
    0.07
    700
    0.07
    cdot
    0.06
    polator
    0.06
    obile
    0.06
     triple
    0.06
    illaume
    0.06
    indsay
    0.06
    Residents
    0.06
     fruition
    0.06
    Act Density 0.000%

    No Known Activations