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

    Neuronpedia

    INDEX
    Explanations

    depend on / upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bedford
    0.39
    າຍ
    0.37
    าย
    0.37
     Новый
    0.37
    ời
    0.36
    ドラゴン
    0.35
    比較
    0.35
    ères
    0.35
    ержа
    0.35
    도시
    0.35
    POSITIVE LOGITS
     upon
    0.89
     depend
    0.68
     heavily
    0.65
     Upon
    0.65
    upon
    0.63
     largely
    0.63
    Upon
    0.61
     greatly
    0.61
     dépend
    0.58
     depended
    0.57
    Act Density 0.022%

    No Known Activations