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

    Neuronpedia

    INDEX
    Explanations

    tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ua
    -0.07
     Joshua
    -0.07
    jiště
    -0.06
     Nigel
    -0.06
    ّل
    -0.06
     sınav
    -0.06
     excellence
    -0.06
    capability
    -0.06
    romo
    -0.06
     caffeine
    -0.06
    POSITIVE LOGITS
    Tree
    0.13
    tree
    0.12
    _tree
    0.10
     tree
    0.10
     Tree
    0.09
    _TREE
    0.09
    -tree
    0.09
     subtree
    0.09
    TREE
    0.08
    	tree
    0.08
    Act Density 0.008%

    No Known Activations