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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    investment
    -0.08
     Packages
    -0.07
    ี↵
    -0.07
     Marino
    -0.07
    $↵
    -0.07
    席
    -0.06
    ！↵
    -0.06
    <div
    -0.06
     "")↵↵
    -0.06
     стратег
    -0.06
    POSITIVE LOGITS
    nému
    0.06
     hei
    0.06
     okuy
    0.06
    　
    0.06
    �
    0.06
    інь
    0.06
     ceny
    0.06
     ambitions
    0.06
    owns
    0.06
     headline
    0.06
    Act Density 0.104%

    No Known Activations