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

    Neuronpedia

    INDEX
    Explanations

    describing character traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     继续访问
    1.01
     \"
    0.90
    \".
    0.89
    \",
    0.87
    <unused61>
    0.86
    </em>
    0.84
    ‚
    0.79
     مشین
    0.79
    \"",
    0.76
     adecuado
    0.75
    POSITIVE LOGITS
    <i>
    1.33
    </b>
    1.01
    <u>
    0.90
     Allan
    0.81
    吟
    0.76
    ellation
    0.70
     character
    0.68
    <b>
    0.67
    0.66
    abase
    0.64
    Act Density 0.000%

    No Known Activations