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

    Neuronpedia

    INDEX
    Explanations

    pronoun them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worldwide
    -0.06
     colder
    -0.06
     senior
    -0.06
     rozum
    -0.06
     برق
    -0.06
     وزار
    -0.06
    -sector
    -0.06
     mee
    -0.06
     Если
    -0.06
     sug
    -0.06
    POSITIVE LOGITS
    _div
    0.08
    askets
    0.07
    TES
    0.06
    /library
    0.06
    .FileInputStream
    0.06
     Girlfriend
    0.06
     tụ
    0.06
    ofilm
    0.06
     Ade
    0.06
    atically
    0.06
    Act Density 0.530%

    No Known Activations