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

    Neuronpedia

    INDEX
    Explanations

    docstring args

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    0.88
    print
    0.86
    playable
    0.83
    :#
    0.81
    printable
    0.76
    অ্যাপ
    0.75
    printk
    0.74
    General
    0.74
    appl
    0.73
    Gradient
    0.73
    POSITIVE LOGITS
     ""
    0.81
     """
    0.79
    ）」
    0.79
     """"
    0.76
     shoving
    0.69
    〟
    0.68
    ་་
    0.67
    」「
    0.67
    ।’’
    0.67
    ,’’
    0.65
    Act Density 0.057%

    No Known Activations