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

    Neuronpedia

    INDEX
    Explanations

    region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    goods
    -0.07
     quits
    -0.07
     quadrant
    -0.07
     brigade
    -0.06
    stops
    -0.06
    ¿
    -0.06
     Donetsk
    -0.06
    urent
    -0.06
    チェ
    -0.06
    Easy
    -0.06
    POSITIVE LOGITS
     believed
    0.06
    นด
    0.06
    (doc
    0.06
    .DataType
    0.06
     erhalten
    0.05
     muddy
    0.05
     жиз
    0.05
    -message
    0.05
     �
    0.05
    enaries
    0.05
    Act Density 0.113%

    No Known Activations