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

    Neuronpedia

    INDEX
    Explanations

    purification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Handles
    -0.07
     rage
    -0.07
     miscon
    -0.07
     yelled
    -0.07
    358
    -0.07
     teenager
    -0.06
    028
    -0.06
    eways
    -0.06
    ńst
    -0.06
    xFE
    -0.06
    POSITIVE LOGITS
     Hampton
    0.07
     Buckingham
    0.07
     Patricia
    0.06
    税
    0.06
     torino
    0.06
     parsley
    0.06
     pur
    0.06
     sulph
    0.06
     pá
    0.06
    ্�
    0.06
    Act Density 0.011%

    No Known Activations