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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RESULT
    -0.07
     mug
    -0.06
    ('<?
    -0.06
    	Color
    -0.06
    (service
    -0.06
     مؤ
    -0.06
    буд
    -0.06
    _word
    -0.06
    anagan
    -0.06
    разу
    -0.06
    POSITIVE LOGITS
    losures
    0.07
    .Be
    0.07
    '};↵
    0.07
        ↵↵
    0.06
     француз
    0.06
    """↵↵
    0.06
    _gate
    0.06
    ратить
    0.06
     Ethan
    0.06
     Hoover
    0.06
    Act Density 0.000%

    No Known Activations