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

    Neuronpedia

    INDEX
    Explanations

    Second person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    担
    -0.07
    ována
    -0.06
     titular
    -0.06
    ột
    -0.06
     waar
    -0.06
    ату
    -0.06
     giải
    -0.06
    _col
    -0.06
     injuring
    -0.06
    Poss
    -0.06
    POSITIVE LOGITS
    ++)↵
    0.08
     seeding
    0.07
    .listen
    0.07
    Hu
    0.07
     additions
    0.07
     hvordan
    0.07
    淡
    0.06
     Foo
    0.06
     Crash
    0.06
    :B
    0.06
    Act Density 0.102%

    No Known Activations