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

    Neuronpedia

    INDEX
    Explanations

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h4>
    1.41
    </b>
    1.29
    </sup>
    1.24
    </sub>
    1.22
     }}$
    1.15
     }}$,
    1.11
    "})
    1.06
    }^{*}$,
    1.00
    </u>
    1.00
     }}$.
    0.99
    POSITIVE LOGITS
    )\
    3.02
    .\
    2.90
    \
    2.79
    ]\
    2.70
    }\
    2.70
    ?\
    2.58
    '\
    2.58
    !\
    2.57
    ).\
    2.52
     )\
    2.46
    Act Density 0.235%

    No Known Activations