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

    Neuronpedia

    INDEX
    Explanations

    manage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     senti
    -0.08
     cavalry
    -0.07
    	aux
    -0.07
     telling
    -0.07
    戻
    -0.07
    เหตุ
    -0.07
     rainbow
    -0.07
     Бол
    -0.07
     రంగ
    -0.07
     личности
    -0.07
    POSITIVE LOGITS
     stewardship
    0.09
     outsourced
    0.09
     नियुक्त
    0.09
    出售
    0.09
    治理
    0.09
     overseeing
    0.08
    classe
    0.08
    sale
    0.08
    负责
    0.08
     designation
    0.08
    Act Density 0.035%

    No Known Activations