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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Haus
    -0.07
     expresses
    -0.07
     آنها
    -0.07
     YEARS
    -0.06
     жовтня
    -0.06
    Пос
    -0.06
    から
    -0.06
     Producto
    -0.06
    ्तव
    -0.06
     damn
    -0.06
    POSITIVE LOGITS
    Pago
    0.06
     Hive
    0.06
    �
    0.06
    静
    0.06
     Oversight
    0.06
    ,V
    0.06
    (right
    0.06
    uv
    0.06
    onds
    0.06
     Miracle
    0.06
    Act Density 0.000%

    No Known Activations