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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     అని
    -0.08
    我国
    -0.08
    ynomial
    -0.08
     তারপর
    -0.08
    然后
    -0.08
    Women
    -0.08
     عورت
    -0.08
    ***↵↵
    -0.08
    *****↵↵
    -0.08
     aquella
    -0.07
    POSITIVE LOGITS
     expertise
    0.08
     motto
    0.08
     som
    0.08
     কর্মক
    0.08
     Korean
    0.07
     worldview
    0.07
     edgy
    0.07
     working
    0.07
     priorities
    0.07
    ック
    0.07
    Act Density 0.173%

    No Known Activations