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

    Neuronpedia

    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frozen
    -0.07
     governo
    -0.07
     janvier
    -0.06
    "But
    -0.06
    (User
    -0.06
    .TAG
    -0.06
    “But
    -0.06
     Plains
    -0.06
     гор
    -0.06
    ，小
    -0.06
    POSITIVE LOGITS
     cresc
    0.06
    оу
    0.06
    mektedir
    0.06
    €€
    0.06
    生き
    0.06
     constit
    0.06
    ์อ
    0.06
    _defined
    0.06
    missible
    0.06
     écrit
    0.06
    Act Density 0.003%

    No Known Activations