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

    Neuronpedia

    INDEX
    Explanations

    showing how to do something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olute
    -0.06
     Kosovo
    -0.06
     FIFO
    -0.06
     amigo
    -0.06
     Poison
    -0.06
     sync
    -0.06
    ÜM
    -0.06
    .note
    -0.06
     haste
    -0.06
     Alonso
    -0.06
    POSITIVE LOGITS
     demonstrate
    0.10
     demonstrating
    0.08
     demonstrations
    0.07
     demonstration
    0.07
     ист
    0.07
     demonstrated
    0.07
    Dist
    0.07
     недостат
    0.07
     accelerometer
    0.07
     demonstrates
    0.06
    Act Density 0.017%

    No Known Activations