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

    Neuronpedia

    INDEX
    Explanations

    reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <em>
    0.50
    <strong>
    0.39
    Madison
    0.39
     Madison
    0.38
    )—
    0.36
     ffilm
    0.35
     incentiv
    0.35
    Giant
    0.34
    Wrap
    0.34
    物质
    0.34
    POSITIVE LOGITS
    </b>
    0.91
    '}}
    0.46
    </i>
    0.46
    <unused60>
    0.43
    "}}
    0.42
    </code>
    0.40
    例文帳に追加
    0.39
    }}:
    0.37
    .}}
    0.36
    unde
    0.35
    Act Density 0.001%

    No Known Activations