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

    Neuronpedia

    INDEX
    Explanations

    Gibberish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "{}
    -0.06
     country
    -0.06
     racked
    -0.06
     случаев
    -0.06
     caveat
    -0.06
    "]),↵
    -0.06
    人才
    -0.06
     trouvé
    -0.06
    яться
    -0.06
     sł
    -0.06
    POSITIVE LOGITS
     nom
    0.07
    _bug
    0.07
     Femin
    0.07
     PRO
    0.07
    porate
    0.07
    erving
    0.07
     eigenen
    0.07
    fed
    0.07
    rolls
    0.06
    /org
    0.06
    Act Density 0.000%

    No Known Activations