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

    Neuronpedia

    INDEX
    Explanations

    decision trees, machine learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CARE
    -0.08
     prie
    -0.07
     enjoy
    -0.07
     write
    -0.07
     accents
    -0.07
     does
    -0.07
     précis
    -0.07
     mod
    -0.07
     suis
    -0.07
     MODE
    -0.07
    POSITIVE LOGITS
     Entscheidungen
    0.11
     decisions
    0.10
     തീരുമാന
    0.10
     Choices
    0.09
     निर्णय
    0.09
    _SPL
    0.09
    pleo
    0.09
     Decisions
    0.09
     splitting
    0.09
    	node
    0.09
    Act Density 0.005%

    No Known Activations