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

    Neuronpedia

    INDEX
    Explanations

    Data splitting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ़े
    -0.07
    -lat
    -0.07
    )a
    -0.07
     quanto
    -0.06
     terrified
    -0.06
     shapes
    -0.06
    коп
    -0.06
     hashmap
    -0.06
    ़ी
    -0.06
     Ш
    -0.06
    POSITIVE LOGITS
     alma
    0.06
     onclick
    0.06
     اندازه
    0.06
    Apr
    0.06
     Indies
    0.06
    :<?
    0.06
     April
    0.06
    ugeot
    0.06
     Sodium
    0.06
     Activ
    0.06
    Act Density 0.003%

    No Known Activations