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

    Neuronpedia

    INDEX
    Explanations

    explaining complex topics simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     继续访问
    0.72
    <em>
    0.70
    </strong>
    0.66
    <strong>
    0.55
    </em>
    0.53
    Pierre
    0.38
     ലൈ
    0.38
    蘑
    0.38
    0.38
    拏
    0.36
    POSITIVE LOGITS
    <b>
    0.76
     例文帳に追加
    0.75
    </i>
    0.72
    例文帳に追加
    0.65
    </b>
    0.55
    }}$,
    0.54
    )}},
    0.52
    }}=\
    0.51
    }}"
    0.51
    )}}
    0.50
    Act Density 0.004%

    No Known Activations