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

    Neuronpedia

    INDEX
    Explanations

    incomplete sentences/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    È
    -0.09
    令
    -0.07
    Ul
    -0.07
    \r
    -0.07
     Ul
    -0.07
     envisioned
    -0.07
     Distrito
    -0.07
     deterg
    -0.07
     doux
    -0.07
    新区
    -0.07
    POSITIVE LOGITS
     achtergrond
    0.08
     pengh
    0.08
     satisfies
    0.08
     respects
    0.08
     Hintergrund
    0.08
    criptions
    0.07
     materiale
    0.07
     resembles
    0.07
     принадлеж
    0.07
     pertenc
    0.07
    Act Density 0.002%

    No Known Activations