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

    Neuronpedia

    INDEX
    Explanations

    new beginnings / beginners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ye
    -0.07
    ráž
    -0.07
     myster
    -0.07
     buildup
    -0.07
     MC
    -0.06
    extr
    -0.06
     QR
    -0.06
    (buffer
    -0.06
     pragma
    -0.06
    NUM
    -0.06
    POSITIVE LOGITS
    Authorization
    0.06
    .swing
    0.06
     Northwestern
    0.06
    /cart
    0.06
    ーター
    0.06
    ersistent
    0.06
    _evaluation
    0.06
     encountering
    0.06
     purchaser
    0.06
    ].'
    0.06
    Act Density 0.036%

    No Known Activations