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

    Neuronpedia

    INDEX
    Explanations

    scientific articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，希望
    -0.09
    hots
    -0.08
    □
    -0.08
     ويح
    -0.08
    Hopefully
    -0.08
     "+
    -0.08
     huizen
    -0.08
    สินค้า
    -0.08
     Hopefully
    -0.08
     irons
    -0.08
    POSITIVE LOGITS
     studies
    0.12
     uuring
    0.10
     эксперт
    0.10
     исследований
    0.10
    发表于
    0.09
     surveys
    0.09
     experts
    0.09
     Studie
    0.09
     Studien
    0.09
    Studies
    0.09
    Act Density 0.032%

    No Known Activations