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

    Neuronpedia

    INDEX
    Explanations

    bold tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <strong>
    0.79
    </em>
    0.73
    <em>
    0.57
      
    0.44
    </strong>
    0.43
     étant
    0.41
    “
    0.40
    </h6>
    0.40
    ‘’
    0.39
        
    0.39
    POSITIVE LOGITS
    碐
    0.53
    </b>
    0.50
     ફાય
    0.43
    㕧
    0.43
    ꩡ
    0.42
    㝅
    0.41
    .}}
    0.41
    注意
    0.41
     問
    0.41
     ylabel
    0.41
    Act Density 0.000%

    No Known Activations