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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code interpolation syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }\
    -0.46
    ])]
    -0.44
    </sup>
    -0.44
     }}$}
    -0.40
    }
    -0.40
    }')
    -0.40
    }")
    -0.39
    ]
    -0.39
    }")]
    -0.38
     OR
    -0.38
    POSITIVE LOGITS
     {{
    1.13
    {{
    1.12
     "{{
    1.10
     '{{
    1.09
    ={{
    1.02
    [{{
    0.99
    >{{
    0.99
    ">{{
    0.97
     ${{
    0.93
    ="{{
    0.92
    Act Density 0.014%

    No Known Activations