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

    Neuronpedia

    INDEX
    Explanations

    lists, collections, and highlights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    두
    0.51
    一
    0.50
    트
    0.49
    Introduction
    0.48
    둘
    0.48
    Defining
    0.47
    하루
    0.47
    т
    0.47
    ICSS
    0.46
    ?"
    0.46
    POSITIVE LOGITS
     didn
    0.61
     hablaremos
    0.56
     يجب
    0.54
    illes
    0.53
     တို့
    0.52
     ମ
    0.49
    odon
    0.49
    ipes
    0.49
     entiende
    0.48
     discuss
    0.47
    Act Density 0.002%

    No Known Activations