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

    Neuronpedia

    INDEX
    Explanations

    delete, official, sanctions, tunnel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     адво
    0.46
    衲
    0.43
     TreeNode
    0.42
     항목
    0.42
     основного
    0.41
    デバイス
    0.40
     കുറ
    0.40
     დიდი
    0.39
     wichtigsten
    0.39
     основным
    0.38
    POSITIVE LOGITS
    網
    0.37
     السيا
    0.36
    তের
    0.36
    ../
    0.34
    Chance
    0.33
    るとき
    0.33
    핳
    0.33
    Therm
    0.33
    Cann
    0.32
     Phnom
    0.32
    Act Density 0.000%

    No Known Activations