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

    Neuronpedia

    INDEX
    Explanations

    Python code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AcOH
    0.54
    CHREIB
    0.54
     Já
    0.54
     オン
    0.53
     Chromatogr
    0.53
     Física
    0.52
     Zusätzlich
    0.52
     バー
    0.52
     CrossFit
    0.52
     Improves
    0.52
    POSITIVE LOGITS
    #
    1.09
    print
    1.04
    def
    0.93
    import
    0.91
    """
    0.86
     print
    0.80
    '''
    0.80
    try
    0.77
    if
    0.75
    from
    0.70
    Act Density 0.841%

    No Known Activations