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

    Neuronpedia

    INDEX
    Explanations

    Python function calls and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溲
    0.34
     Strept
    0.32
    URNIZOR
    0.32
     መድ
    0.29
    牖
    0.29
    畋
    0.29
     //-
    0.29
    骢
    0.29
     સંપૂર્ણ
    0.28
    -//
    0.27
    POSITIVE LOGITS
    try
    0.64
    """
    0.61
    print
    0.60
    #
    0.56
    kwargs
    0.52
    '''
    0.50
    elif
    0.49
    pygame
    0.49
     print
    0.47
    ##
    0.45
    Act Density 0.176%

    No Known Activations