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

    Neuronpedia

    INDEX
    Explanations

    python code definitions and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $"{
    0.45
    }~
    0.43
     }+\
    0.43
    驄
    0.42
    抚
    0.40
    髡
    0.40
    ᒫ
    0.40
     phasor
    0.40
    ᖕ
    0.39
    ็จ
    0.39
    POSITIVE LOGITS
    def
    1.43
     def
    1.13
    import
    1.00
    """
    0.82
     Def
    0.78
    #
    0.78
    #!/
    0.77
    print
    0.77
    '''
    0.73
    from
    0.72
    Act Density 0.126%

    No Known Activations