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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Series
    -0.07
     eastern
    -0.07
     drones
    -0.07
    _eta
    -0.06
    aria
    -0.06
     понять
    -0.06
    -upper
    -0.06
     �
    -0.06
     Dragon
    -0.06
     phí
    -0.06
    POSITIVE LOGITS
     Alexandria
    0.06
     LoggerFactory
    0.06
    355
    0.06
    utzt
    0.06
     Leonardo
    0.06
    Arial
    0.06
     sağlam
    0.06
     chuck
    0.06
     incredible
    0.06
     Học
    0.06
    Act Density 0.010%

    No Known Activations