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

    Neuronpedia

    INDEX
    Explanations

    training and learned skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    忆
    -1.52
    𖤍
    -1.45
     chère
    -1.40
     África
    -1.35
    獃
    -1.34
     \"
    -1.34
    红的
    -1.33
    絝
    -1.32
     "
    -1.31
    Printer
    -1.30
    POSITIVE LOGITS
    ܖ
    1.53
    ;
    1.43
    </b>
    1.40
     richtigen
    1.32
     to
    1.31
     pomaga
    1.30
     result
    1.30
    mathrm
    1.30
    可以
    1.30
     Kartoffeln
    1.29
    Act Density 0.038%

    No Known Activations