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
     цент
    -0.07
    ?>↵↵↵
    -0.06
     IconButton
    -0.06
     {↵↵↵↵
    -0.06
    τών
    -0.06
     [...
    -0.06
    Although
    -0.06
    ısında
    -0.06
    ！！↵↵
    -0.06
     {↵↵↵
    -0.06
    POSITIVE LOGITS
     населення
    0.07
     preparation
    0.06
     treasures
    0.06
     Tanner
    0.06
     Amateur
    0.06
     her
    0.06
    /package
    0.06
    действ
    0.06
     revolution
    0.06
     methodology
    0.06
    Act Density 0.030%

    No Known Activations