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

    Neuronpedia

    INDEX
    Explanations

    right subtree partitioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kemenangan
    0.52
    าราง
    0.48
     najważ
    0.44
     acciaio
    0.44
     protéines
    0.43
     acier
    0.43
     négoci
    0.43
     כת
    0.42
     نرخ
    0.42
     polož
    0.42
    POSITIVE LOGITS
    subtree
    0.63
     subtree
    0.62
     left
    0.58
    left
    0.54
     tree
    0.52
     Tree
    0.52
    树
    0.51
     children
    0.49
     right
    0.48
     Lateral
    0.47
    Act Density 0.033%

    No Known Activations