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

    Neuronpedia

    INDEX
    Explanations

    repro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubic
    -0.06
    naz
    -0.06
    maj
    -0.06
    σ
    -0.06
    借
    -0.06
    £
    -0.06
    CONN
    -0.06
     Lucas
    -0.06
     swords
    -0.06
     maj
    -0.05
    POSITIVE LOGITS
     reperc
    0.08
     آثار
    0.07
     ranger
    0.07
     국내
    0.07
     repr
    0.07
    ObjectOfType
    0.07
    (filter
    0.07
    Billing
    0.07
     wieder
    0.07
     unread
    0.07
    Act Density 0.003%

    No Known Activations