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

    Neuronpedia

    INDEX
    Explanations

    People pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     国产
    -0.07
    .rank
    -0.07
     overwhelmed
    -0.07
    ункт
    -0.06
     技
    -0.06
     اسپ
    -0.06
    Teams
    -0.06
    _globals
    -0.06
     Challenges
    -0.06
    unless
    -0.06
    POSITIVE LOGITS
    ystal
    0.06
     renovated
    0.06
    ROLLER
    0.06
    jem
    0.06
    ..<
    0.06
    osy
    0.06
    asic
    0.06
     Stunden
    0.06
     Preparation
    0.06
    ieri
    0.06
    Act Density 0.006%

    No Known Activations