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

    Neuronpedia

    INDEX
    Explanations

    Accounting software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .')
    1.03
    ;')
    0.95
    ;)
    0.91
     '.')
    0.88
    `)
    0.87
    !')
    0.87
    ;'
    0.86
    ;.
    0.83
    ]
    0.82
    ;*/
    0.82
    POSITIVE LOGITS
    "):
    3.09
    ()):
    2.82
    ):
    2.79
    '):
    2.75
     "):
    2.73
     ):
    2.73
    )):
    2.67
    "]:
    2.66
    ）：
    2.66
    ']:
    2.60
    Act Density 0.942%

    No Known Activations