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

    Neuronpedia

    INDEX
    Explanations

    materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     страницы
    -0.08
    节目
    -0.08
     ofrece
    -0.08
    -0.08
     مر
    -0.08
    گر
    -0.08
     genial
    -0.08
     provoca
    -0.08
     Yuri
    -0.08
     stránky
    -0.08
    POSITIVE LOGITS
     contribution
    0.10
     insertion
    0.09
    direct
    0.09
     directly
    0.08
    Direct
    0.08
     contributions
    0.08
     contributing
    0.08
    .Direct
    0.08
     ఆట
    0.08
    _direct
    0.08
    Act Density 0.006%
    No Known Activations