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

    Neuronpedia

    INDEX
    Explanations

    data structures and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Interpreter
    0.38
    rombin
    0.38
     stylu
    0.37
    Interpreter
    0.37
     Bourd
    0.37
    generator
    0.37
    Caption
    0.36
     Liebig
    0.36
     demethyl
    0.36
     statistique
    0.36
    POSITIVE LOGITS
     Structures
    0.59
     HashTable
    0.58
    Structures
    0.57
    structures
    0.54
    datast
    0.52
     efficient
    0.51
     structures
    0.51
     Hash
    0.51
    DS
    0.50
    Hash
    0.50
    Act Density 0.013%

    No Known Activations